© 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. 243770
    Prev
    Next
    INDEX
    Explanations

    pricing per person

    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
    ভূম
    0.49
    сед
    0.49
    மதி
    0.49
     стать
    0.49
    Vue
    0.49
    垕
    0.48
    Czas
    0.48
    ட
    0.47
    き
    0.47
    🥃
    0.47
    POSITIVE LOGITS
     austral
    0.47
     grievances
    0.47
     bacteria
    0.46
     pathogenicity
    0.46
     Australian
    0.46
     juli
    0.45
     variants
    0.44
     physiological
    0.44
     eukary
    0.44
     rask
    0.43
    Activations Density 0.001%

    No Known Activations