© 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. 33109
    Prev
    Next
    INDEX
    Explanations

    EV documents, unfriendly, loans, these texts

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

    non-english words

    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
     projections
    0.47
     it
    0.46
    wealth
    0.46
     a
    0.45
     slut
    0.45
    ?
    0.45
    projection
    0.45
     wealth
    0.44
     viewHolder
    0.43
     може
    0.43
    POSITIVE LOGITS
    āb
    0.52
    aparikkh
    0.50
     單
    0.47
    atthena
    0.44
     Wörter
    0.43
     プリント
    0.43
    īd
    0.43
    abhuto
    0.43
    リット
    0.42
    ត្ថ
    0.42
    Activations Density 0.000%

    No Known Activations