© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49801
    Prev
    Next
    INDEX
    Explanations

    out from

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

    This neuron activates on the particles and prepositions in multiword “phrasal verbs” expressing removal or movement (e.g. out, from, under, away).

    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
    innerHeight
    -0.75
     probleem
    -0.75
     reen
    -0.72
    Géographie
    -0.72
    ব
    -0.70
    PROTECT
    -0.69
     hasard
    -0.68
     problème
    -0.66
     Tierney
    -0.66
     flexibility
    -0.66
    POSITIVE LOGITS
     from
    1.40
     emerge
    1.20
     spod
    1.09
     emerged
    1.06
     From
    0.99
     out
    0.98
    From
    0.96
     emergence
    0.96
    from
    0.95
     FROM
    0.95
    Activations Density 0.027%

    No Known Activations