© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37717
    Prev
    Next
    INDEX
    Explanations

    an/a followed by time unit

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

    writing or coding assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agreement
    0.46
    emotion
    0.44
    普通的
    0.44
    ام
    0.43
    idar
    0.42
    ق
    0.42
    <0xAC>
    0.42
    १
    0.42
    יל
    0.42
    不说
    0.41
    POSITIVE LOGITS
     brzo
    0.59
     mùa
    0.59
     書き
    0.53
     aata
    0.52
     fille
    0.51
     writers
    0.51
     permettent
    0.51
     znan
    0.51
     brou
    0.50
     writer
    0.50
    Activations Density 0.000%

    No Known Activations