© 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. 28544
    Prev
    Next
    INDEX
    Explanations

    on tap, truck_, Natural Flav

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

    you, you're, you don't

    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
    ↵
    0.52
    =
    0.46
    utta
    0.45
    у
    0.45
    Lewis
    0.44
    usto
    0.44
    ip
    0.43
    is
    0.43
    ato
    0.42
    igny
    0.42
    POSITIVE LOGITS
     suasana
    0.56
     డై
    0.52
     डाय
    0.49
     రిడి
    0.48
     ডায়
    0.48
     pengunjung
    0.48
    𝐷
    0.48
    రె
    0.46
     radionuclides
    0.46
     hormati
    0.46
    Activations Density 0.000%

    No Known Activations