© 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. 16198
    Prev
    Next
    INDEX
    Explanations

    parts of a whole

    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
    in
    1.13
    of
    1.00
    ERS
    0.93
    v
    0.84
    0
    0.80
    ik
    0.79
    BL
    0.78
    5
    0.76
    BU
    0.76
    pt
    0.74
    POSITIVE LOGITS
     datth
    0.85
    人不
    0.82
     obstruct
    0.82
     gratuits
    0.82
     nebude
    0.81
    risch
    0.80
     estará
    0.80
     distraught
    0.79
     poté
    0.78
     cél
    0.77
    Activations Density 0.016%

    No Known Activations