© 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. 26346
    Prev
    Next
    INDEX
    Explanations

    roughness

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

    rough visual approximation

    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
    un
    0.46
    amed
    0.45
    🗽
    0.44
     Policies
    0.44
    並不
    0.43
     fà
    0.43
     पॉलिसी
    0.43
     nowadays
    0.42
     políticas
    0.42
    ുകയാണ്
    0.42
    POSITIVE LOGITS
    粗
    0.50
     rough
    0.45
    所需
    0.45
     miss
    0.45
     కోసం
    0.44
     SIDE
    0.44
     干
    0.43
     ξ
    0.43
     ژ
    0.43
     Dirac
    0.43
    Activations Density 0.000%

    No Known Activations