© 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. 210761
    Prev
    Next
    INDEX
    Explanations

    non-is perfectthe horizontaldo-it-yourselfdesigners andincluding Tahoeare specifichappens.sessions,flights,

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

    crisis line or emergencies

    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
    궁
    0.48
    "]);
    0.47
    ద్దా
    0.45
    وین
    0.44
    ི
    0.44
    ერი
    0.44
    ین
    0.43
    ેર
    0.43
    ایک
    0.43
    اری
    0.43
    POSITIVE LOGITS
    risa
    0.53
     использование
    0.51
    abel
    0.50
    respon
    0.50
     начало
    0.50
    yaxis
    0.50
    р
    0.49
    BA
    0.49
    比賽
    0.48
    tot
    0.47
    Activations Density 0.000%

    No Known Activations