© 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. 56047
    Prev
    Next
    INDEX
    Explanations

    Python code constructs and punctuation

    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
     நாம்
    0.35
     모
    0.34
    每個
    0.32
    }`))
    0.32
    Spider
    0.31
    டியில்
    0.31
     맞
    0.31
     კონ
    0.31
     레
    0.31
    ECTION
    0.31
    POSITIVE LOGITS
     britannique
    0.33
     thrombo
    0.32
     humoral
    0.32
     hukum
    0.32
     نہيں
    0.32
     placebo
    0.31
     enggak
    0.30
     doskona
    0.30
     وګټ
    0.30
     carboxylic
    0.30
    Activations Density 0.225%

    No Known Activations