© 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. 35777
    Prev
    Next
    INDEX
    Explanations

    system building blocks

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

    one-size-fits-all

    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
     percentuale
    0.48
     arrondies
    0.47
     causada
    0.47
    ໃນ
    0.46
     dihedral
    0.46
     উত্তেজনা
    0.43
    阿
    0.43
     Lors
    0.42
     Ideally
    0.42
     阿
    0.41
    POSITIVE LOGITS
    knowledge
    0.49
    v
    0.48
    solution
    0.45
    ystem
    0.45
    access
    0.45
    datab
    0.44
    ght
    0.44
    elfare
    0.43
    position
    0.42
    system
    0.42
    Activations Density 0.000%

    No Known Activations