© 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. 36965
    Prev
    Next
    INDEX
    Explanations

    old days

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

    person, specific, spiritual, they, most

    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
    تباينه
    0.44
     செயல்
    0.43
    দো
    0.41
    ادو
    0.41
    ками
    0.41
    瑚
    0.41
    𝕕
    0.40
    㕕
    0.40
     limitar
    0.40
     achat
    0.39
    POSITIVE LOGITS
     тебя
    0.55
     вспо
    0.48
     збере
    0.46
    0.46
    urais
    0.45
    itary
    0.45
     Membuat
    0.45
     Від
    0.45
     पिट
    0.45
    ?
    0.44
    Activations Density 0.001%

    No Known Activations