© 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. 79977
    Prev
    Next
    INDEX
    Explanations

    system in, method as

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

    historical context or bias

    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
    Submit
    0.46
    Customer
    0.45
    Targets
    0.45
     scammers
    0.45
     selles
    0.45
     checks
    0.43
    Checks
    0.43
    ޮ
    0.43
    OGLE
    0.42
    Focused
    0.42
    POSITIVE LOGITS
    fif
    0.45
    outheast
    0.44
    opor
    0.43
    ggak
    0.43
     Redistributions
    0.43
    yst
    0.43
     Artillery
    0.42
    }{{
    0.42
    ogeneous
    0.41
    ühle
    0.41
    Activations Density 0.007%

    No Known Activations