© 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. 69183
    Prev
    Next
    INDEX
    Explanations

    savings, adjust, logo, sizes

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

    least disruptive or complex

    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
     Bienvenido
    0.46
     hyperbolic
    0.45
     firmware
    0.42
    十
    0.40
    、
    0.40
     cryptocurrency
    0.40
     Symfony
    0.39
     Figma
    0.39
     purification
    0.39
     executable
    0.39
    POSITIVE LOGITS
    mostly
    0.48
     větš
    0.47
     ఎక్కువగా
    0.46
    یعنی
    0.46
    count
    0.45
    assess
    0.44
    さすが
    0.44
    counts
    0.43
    鰥
    0.43
    ਸੀਂ
    0.42
    Activations Density 0.002%

    No Known Activations