© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55193
    Prev
    Next
    INDEX
    Explanations

    push you out of danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝐬
    0.56
     новая
    0.54
     дорого
    0.52
     অনিবার
    0.52
    كُمْ
    0.51
     (\$
    0.51
    凃
    0.50
    itys
    0.50
    硙
    0.49
    ソニック
    0.49
    POSITIVE LOGITS
    ?
    0.44
     charge
    0.43
     L
    0.43
    The
    0.43
     or
    0.42
     leak
    0.42
    ↵
    0.42
    汚れ
    0.42
     The
    0.42
     conversation
    0.42
    Activations Density 0.001%

    No Known Activations