© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71922
    Prev
    Next
    INDEX
    Explanations

    broadcaster, musician, attacker, know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stratég
    -0.98
     női
    -0.94
     MONT
    -0.93
     normalt
    -0.92
     здоров
    -0.91
    🔉
    -0.91
     ТАК
    -0.90
    靭
    -0.90
     megjelen
    -0.90
     accesses
    -0.90
    POSITIVE LOGITS
     broadcaster
    1.06
    canos
    1.03
    ECAUSE
    1.01
     musician
    1.01
    skou
    0.94
    。」
    0.93
     throwback
    0.89
     attacker
    0.88
     know
    0.88
     where
    0.86
    Activations Density 0.001%

    No Known Activations