© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45179
    Prev
    Next
    INDEX
    Explanations

    help action

    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_65k_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
    הר
    0.52
    ש
    0.52
    ৰ
    0.50
    ה
    0.50
    ב
    0.50
    스
    0.49
    𝘀
    0.49
    Ка
    0.48
    Су
    0.47
    Ε
    0.47
    POSITIVE LOGITS
    riev
    0.42
     Pla
    0.41
    ouveau
    0.40
     involvement
    0.40
     Douglass
    0.40
    jacking
    0.40
    rhe
    0.40
     Fudge
    0.39
    agi
    0.39
    idelity
    0.39
    Activations Density 0.007%

    No Known Activations