© 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. 172789
    Prev
    Next
    INDEX
    Explanations

    products, devices, villages, paperback, informe

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

    right sequence / check this / times this

    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
    ტიკ
    0.51
    т
    0.51
     geoLocation
    0.50
    ীয়
    0.50
    се
    0.47
    В
    0.46
    Decl
    0.45
    ஜ
    0.45
    ⵡ
    0.45
    Geolocation
    0.44
    POSITIVE LOGITS
    ζεται
    0.47
     spé
    0.46
     Peralta
    0.45
     Brat
    0.44
    簡単な
    0.43
    فته
    0.42
     qualit
    0.41
     plas
    0.41
     sau
    0.40
     நாங்கள்
    0.40
    Activations Density 0.001%

    No Known Activations