© 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. 30973
    Prev
    Next
    INDEX
    Explanations

    quantities after "to"

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

    slightly

    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
     사람
    0.41
    粙
    0.40
     drastically
    0.40
    时代
    0.39
     extrêmement
    0.38
    τικές
    0.37
    数十
    0.37
    ⨯
    0.37
     оказа
    0.37
     aucun
    0.37
    POSITIVE LOGITS
     slightly
    0.82
    slightly
    0.70
     Slightly
    0.66
     légèrement
    0.60
     немного
    0.53
     थोड़ा
    0.52
     ligeramente
    0.50
    稍微
    0.49
     немно
    0.43
     Slight
    0.43
    Activations Density 0.119%

    No Known Activations