© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112211
    Prev
    Next
    INDEX
    Explanations

    crucial or sophisticated developing

    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_31_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
    ១
    0.51
    angled
    0.46
    confusion
    0.46
    compiled
    0.45
    ды
    0.44
    type
    0.43
    detection
    0.42
    mathscr
    0.42
    ‌است
    0.42
    common
    0.42
    POSITIVE LOGITS
    ;
    0.49
     č
    0.48
     Government
    0.46
     w
    0.46
     Cadillac
    0.45
     debt
    0.45
     k
    0.44
     v
    0.44
     Ala
    0.44
     za
    0.44
    Activations Density 0.011%

    No Known Activations