© 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. 201310
    Prev
    Next
    INDEX
    Explanations

    cause another

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

    prefers understatement or concise

    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
    FCO
    0.43
     headerShown
    0.43
     ମ
    0.43
    ಿಸಲ
    0.43
     കാഴ്ച
    0.43
     понравилось
    0.43
     ASN
    0.42
     |,
    0.42
     !!,
    0.42
     empowerment
    0.42
    POSITIVE LOGITS
    productos
    0.47
    $
    0.47
    zahl
    0.46
     curvy
    0.45
     producción
    0.45
    失
    0.45
    ola
    0.44
    bal
    0.44
    los
    0.44
    k
    0.44
    Activations Density 0.000%

    No Known Activations