© 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. 41804
    Prev
    Next
    INDEX
    Explanations

    custom code, standards, scholarship

    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
     interpreter
    0.43
     servent
    0.39
     reinterpret
    0.39
     verwendeten
    0.38
     brackets
    0.38
     പറയുന്നത്
    0.38
    },}
    0.38
     tượng
    0.37
     дозво
    0.37
     constructions
    0.37
    POSITIVE LOGITS
    cji
    0.43
    AAC
    0.42
     CIA
    0.42
    WAN
    0.42
     MPI
    0.42
    𝗣
    0.41
     MICHAEL
    0.40
    veston
    0.40
     CNS
    0.40
     CIN
    0.40
    Activations Density 0.002%

    No Known Activations