© 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. 762
    Prev
    Next
    INDEX
    Explanations

    basic concepts, licensing terms, under consideration

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

    numbers and percentages

    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
    ోధ
    0.55
     bất
    0.53
    я
    0.53
    اش
    0.52
    اط
    0.52
     flaws
    0.50
    јединачна
    0.49
    Но
    0.49
    𝒉
    0.49
    Პ
    0.49
    POSITIVE LOGITS
     (
    0.46
     P
    0.45
     OS
    0.44
     Cameron
    0.44
     sortie
    0.43
     roof
    0.42
    ))
    0.42
     Andrew
    0.42
     PubMed
    0.41
     MIM
    0.41
    Activations Density 0.000%

    No Known Activations