© 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. 156542
    Prev
    Next
    INDEX
    Explanations

    describes ability offers

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

    potential drawbacks or personality

    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
     analogous
    0.50
     giugno
    0.47
    ୩
    0.45
    णा
    0.44
     trespass
    0.44
    ید
    0.44
     coloc
    0.44
     administered
    0.43
    ጽ
    0.43
    8
    0.42
    POSITIVE LOGITS
     संस्कारों
    0.52
    o
    0.52
    vak
    0.52
    akad
    0.50
    heil
    0.48
    imit
    0.48
    ází
    0.47
    setAdapter
    0.47
    hö
    0.46
    ie
    0.45
    Activations Density 0.000%

    No Known Activations