© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52422
    Prev
    Next
    INDEX
    Explanations

    direct accusation or sequence progression

    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
     vacc
    0.56
     ocho
    0.48
     IIS
    0.47
     STATEMENT
    0.47
     cento
    0.47
     cárc
    0.47
    𝐤
    0.47
     göz
    0.47
     oito
    0.47
     websocket
    0.46
    POSITIVE LOGITS
    ting
    0.52
    data
    0.52
    amin
    0.52
    amu
    0.51
    hain
    0.50
    am
    0.50
    ay
    0.50
    缘
    0.49
    ati
    0.47
    db
    0.47
    Activations Density 0.003%

    No Known Activations