© 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. 15488
    Prev
    Next
    INDEX
    Explanations

    our own words

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

    often just, relying solely

    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
    ಾಸ
    0.45
    file
    0.44
    foot
    0.44
    venture
    0.40
    ולים
    0.40
    硐
    0.40
    rian
    0.39
    casino
    0.39
    転職
    0.38
    cash
    0.38
    POSITIVE LOGITS
     disapproved
    0.55
     prese
    0.49
    ക്കെ
    0.48
     Negev
    0.48
     detal
    0.48
     sadde
    0.48
    }]$.
    0.46
     archaic
    0.46
     Nauchno
    0.46
     animali
    0.46
    Activations Density 0.000%

    No Known Activations