© 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. 29652
    Prev
    Next
    INDEX
    Explanations

    speaking groups

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

    qualifiers and descriptions

    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
    嘞
    0.48
     spol
    0.46
    SIN
    0.44
    Sine
    0.43
    lare
    0.43
    Duc
    0.42
     femelles
    0.41
    lte
    0.41
    SING
    0.41
     दू
    0.40
    POSITIVE LOGITS
    ן
    0.47
     Kopf
    0.45
    공
    0.43
    িব
    0.42
     gitti
    0.42
    abcdef
    0.42
    anged
    0.41
     Bahkan
    0.40
    עות
    0.39
    Ő
    0.39
    Activations Density 0.000%

    No Known Activations