© 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. 162538
    Prev
    Next
    INDEX
    Explanations

    moon visits

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

    conditions and requirements

    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
    うち
    0.52
    ား
    0.50
    incre
    0.50
     fermé
    0.50
     continuité
    0.50
    驢
    0.50
    蚛
    0.49
    ută
    0.49
    㧣
    0.47
    ீர்க
    0.47
    POSITIVE LOGITS
     cartil
    0.50
     also
    0.48
     Abschnitt
    0.48
    និង
    0.47
     wilt
    0.47
     beinhaltet
    0.46
    ></
    0.46
    =
    0.46
    ።
    0.45
     Wayback
    0.45
    Activations Density 0.000%

    No Known Activations