© 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. 30301
    Prev
    Next
    INDEX
    Explanations

    reduces, mean, systems, hour

    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
    ulele
    0.46
    <0x8F>
    0.45
    aldehyde
    0.38
    GreaterThan
    0.38
    ొక్క
    0.37
     Midway
    0.37
    📮
    0.37
    วรร
    0.37
    antage
    0.37
     vời
    0.37
    POSITIVE LOGITS
     πολυ
    0.37
    peasants
    0.37
    pom
    0.36
    萌
    0.35
    prevent
    0.34
     Θε
    0.34
    taxes
    0.34
     Omb
    0.34
     заду
    0.33
     смог
    0.33
    Activations Density 0.002%

    No Known Activations