© 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-262K
    7. 90426
    Prev
    Next
    INDEX
    Explanations

    understand, listening, hearing

    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
     drawing
    0.47
     antidepressant
    0.45
     meat
    0.43
     viewfinder
    0.43
     cardinality
    0.41
    呥
    0.41
     tuxedo
    0.41
     circumcision
    0.40
    lastCursor
    0.40
    ंतिक
    0.40
    POSITIVE LOGITS
    us
    0.40
    ैर
    0.40
     선
    0.40
    nde
    0.39
    rakt
    0.38
    z
    0.38
    rak
    0.37
    jt
    0.37
     overhe
    0.37
     запас
    0.36
    Activations Density 0.006%

    No Known Activations