© 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. 137139
    Prev
    Next
    INDEX
    Explanations

    docker type definitions

    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
     in
    0.53
    f
    0.50
    ta
    0.47
     carr
    0.47
    ers
    0.46
    rtle
    0.46
    P
    0.45
    tier
    0.44
     exclusivo
    0.43
     Trojans
    0.43
    POSITIVE LOGITS
    Ꮘ
    0.51
    дования
    0.47
    詠
    0.47
    ння
    0.47
    ยิน
    0.47
    примеча
    0.46
    стави
    0.46
     ductility
    0.45
     efeito
    0.45
     bravery
    0.45
    Activations Density 0.001%

    No Known Activations