© 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. 91897
    Prev
    Next
    INDEX
    Explanations

    deceive, cause, understand, indicative, hook

    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
     ขั้น
    0.52
     Ư
    0.52
    ℧
    0.52
    StdHandle
    0.51
    vish
    0.51
    salaryfrom
    0.50
     GameOver
    0.50
     Pupils
    0.50
     تلاميذ
    0.50
     Feet
    0.49
    POSITIVE LOGITS
    AN
    0.52
     be
    0.49
    *
    0.48
    ,
    0.48
     beatae
    0.46
    ;
    0.45
    【
    0.45
     modification
    0.44
     coerced
    0.43
    •
    0.43
    Activations Density 0.001%

    No Known Activations