© 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. 51477
    Prev
    Next
    INDEX
    Explanations

    structured text and code

    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
     be
    0.60
     as
    0.59
     for
    0.51
     are
    0.50
     yarns
    0.48
     is
    0.44
     ب
    0.44
     د
    0.44
     Onc
    0.43
     Brief
    0.42
    POSITIVE LOGITS
    besiege
    0.55
    ນາ
    0.53
     všetky
    0.46
     టిప్పు
    0.46
    Flicky
    0.46
    StillWater
    0.44
    дал
    0.42
     způ
    0.42
     አለበት
    0.41
    čiť
    0.41
    Activations Density 0.009%

    No Known Activations