© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48128
    Prev
    Next
    INDEX
    Explanations

    detachable or removable

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on phrasing that describes parts being detachably attached (e.g. “detachably installed,” “deta­chably securing”), i.e. language about components that can be removed or affixed.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fahrts
    -0.69
    solo
    -0.69
    tructor
    -0.68
    lane
    -0.66
    Solo
    -0.65
    ignées
    -0.65
    批
    -0.65
     القديمة
    -0.64
    itola
    -0.64
     Дру
    -0.63
    POSITIVE LOGITS
     removable
    5.13
     Removable
    3.88
     detachable
    3.72
    remo
    3.22
    Remo
    3.17
     съем
    2.97
     REMOV
    2.55
    REMOV
    2.53
     remove
    2.47
     removal
    2.44
    Activations Density 0.112%

    No Known Activations