© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11770
    Prev
    Next
    INDEX
    Explanations

    the + proper noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    áctica
    0.51
     zowel
    0.49
     a
    0.48
    🔛
    0.46
     Desde
    0.45
    双方
    0.44
     the
    0.44
    𝑓
    0.43
    jenja
    0.43
    拿出
    0.43
    POSITIVE LOGITS
    atrical
    1.01
    odore
    1.00
    lma
    0.84
    ophylline
    0.81
    matic
    0.79
    odora
    0.76
    mselves
    0.70
     importance
    0.69
    ophilus
    0.67
    atres
    0.67
    Activations Density 0.038%

    No Known Activations