© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48440
    Prev
    Next
    INDEX
    Explanations

    arithmetic and programming syntax

    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_16_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
     to
    0.65
    ua
    0.63
    ।
    0.59
    𝟐
    0.59
    𝟎
    0.58
     на
    0.55
     из
    0.54
     лег
    0.54
     ();
    0.54
     पहुंचकर
    0.54
    POSITIVE LOGITS
    y
    0.78
    _
    0.65
    ↵
    0.59
    ം
    0.58
    a
    0.57
     Tempat
    0.57
    েরই
    0.57
    డ్డి
    0.56
    0.56
     Paraguay
    0.55
    Activations Density 0.209%

    No Known Activations