© 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. 145152
    Prev
    Next
    INDEX
    Explanations

    wise to

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

    last punctuation or end marker

    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
    桦
    0.48
     ciągu
    0.45
    广播
    0.44
     Cabinet
    0.43
    <unused244>
    0.43
     Julia
    0.42
    驿
    0.42
    วา
    0.41
    股价
    0.41
    센터
    0.40
    POSITIVE LOGITS
    ମ୍
    0.54
     atth
    0.45
     worshippers
    0.45
    pneum
    0.44
    ವರ
    0.44
    omist
    0.44
     personen
    0.44
     vegans
    0.43
    causes
    0.43
     plumbers
    0.43
    Activations Density 0.000%

    No Known Activations