© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1608
    Prev
    Next
    INDEX
    Explanations

    listing values after keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harsher
    0.99
     amyloid
    0.99
    츈
    0.98
     abiding
    0.98
    स्टिव
    0.97
     professed
    0.97
     hybridization
    0.96
    鏗
    0.96
    キュリティ
    0.96
    ᓱ
    0.96
    POSITIVE LOGITS
    માં
    0.98
    ে
    0.98
     iremos
    0.94
     Lead
    0.94
    )<<
    0.93
    лайте
    0.92
    स
    0.92
    ie
    0.89
    `,`
    0.89
     frente
    0.89
    Activations Density 0.000%

    No Known Activations