© 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. 220716
    Prev
    Next
    INDEX
    Explanations

    repeated or same

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

    caution against

    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
    やか
    0.52
     malignancy
    0.47
    >
    0.45
    ない
    0.44
    Ini
    0.43
    malign
    0.42
     prematurely
    0.42
     malignancies
    0.42
     hated
    0.41
     malign
    0.41
    POSITIVE LOGITS
    ៀង
    0.55
     valamint
    0.52
     sebag
    0.50
    движи
    0.50
    筤
    0.50
     kapcsol
    0.48
     whaka
    0.47
     जलाने
    0.46
    ubehör
    0.46
     WWF
    0.46
    Activations Density 0.000%

    No Known Activations