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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78161
    Prev
    Next
    INDEX
    Explanations

    states inability

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

    The neuron is activated by multi‐digit numeric tokens (i.e. longer numbers).

    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
     estranho
    -0.84
     станет
    -0.77
    ieuse
    -0.76
     limpo
    -0.76
     特集
    -0.75
     памя
    -0.74
     questions
    -0.73
     داشت
    -0.72
    メット
    -0.71
     Different
    -0.71
    POSITIVE LOGITS
     unable
    6.16
    unable
    4.56
    Unable
    4.38
     Unable
    4.22
     inability
    4.09
     incapable
    3.80
     cannot
    3.34
    无法
    3.08
     incapa
    2.88
    Cannot
    2.86
    Activations Density 0.126%

    No Known Activations