© 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-65K
    7. 51594
    Prev
    Next
    INDEX
    Explanations

    arm circles

    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_65k_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
    剤
    0.42
    拨款
    0.39
    㳖
    0.39
     թ
    0.38
    䓶
    0.38
    辔
    0.38
     بُ
    0.37
    ંદ્ર
    0.36
    耖
    0.36
    ጄ
    0.36
    POSITIVE LOGITS
     Angebot
    0.47
     Input
    0.46
     disponible
    0.45
     Leser
    0.45
     repurchase
    0.44
     assessed
    0.44
     bizarre
    0.44
     XOR
    0.44
     screened
    0.43
     INPUT
    0.43
    Activations Density 0.014%

    No Known Activations