© 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. 12941
    Prev
    Next
    INDEX
    Explanations

    file paths and software

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

    programming identifiers and keywords

    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
     případě
    0.44
    ']].
    0.42
    größe
    0.41
    ರದ
    0.41
    ámicas
    0.40
    󰀄
    0.40
    برای
    0.39
     findPlayer
    0.39
    querysearch
    0.39
     describir
    0.39
    POSITIVE LOGITS
    ెం
    0.44
     Mainland
    0.40
     കീഴ
    0.39
     े
    0.38
     pounds
    0.38
     Lands
    0.38
     Nour
    0.38
     Cro
    0.37
     Council
    0.37
     Svet
    0.37
    Activations Density 0.000%

    No Known Activations