© 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. 209788
    Prev
    Next
    INDEX
    Explanations

    historic questions, Jehovah's Witnesses, plate goes

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

    . instruction prompt

    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
    ALS
    0.47
    IN
    0.44
    ISM
    0.44
    Zeit
    0.44
    }=-\
    0.43
     מא
    0.43
    Ruth
    0.43
    Cuánto
    0.43
    Nguyen
    0.43
    Klein
    0.42
    POSITIVE LOGITS
    ovací
    0.44
    缬
    0.44
    ardonnay
    0.43
    สรร
    0.42
    <0x92>
    0.41
    leges
    0.40
     rownames
    0.40
    ációs
    0.40
     vadd
    0.40
    igheder
    0.40
    Activations Density 0.001%

    No Known Activations