© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136925
    Prev
    Next
    INDEX
    Explanations

    about what, heart, metal, looked much

    np_acts-logits-general · gemini-2.5-flash-lite

    common interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     November
    0.49
    $--
    0.46
    隐私
    0.46
    yleg
    0.45
     честь
    0.45
    Samuel
    0.44
     February
    0.44
    Sao
    0.44
     Samuel
    0.44
    يه
    0.43
    POSITIVE LOGITS
    ₂,
    0.49
     litro
    0.48
     earths
    0.44
     equilib
    0.44
     alumin
    0.44
     abil
    0.44
     monoch
    0.44
     earthenware
    0.43
    পোর
    0.43
    şik
    0.43
    Activations Density 0.001%

    No Known Activations