© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74888
    Prev
    Next
    INDEX
    Explanations

    C/C++ code snippets

    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
    }}$,
    0.52
     sebagai
    0.44
    gehen
    0.44
    phobic
    0.44
    ،
    0.43
    ometown
    0.42
    вает
    0.42
     جائے۔
    0.42
    ventures
    0.42
    ക്കുന്ന
    0.42
    POSITIVE LOGITS
     Strang
    0.46
     उन्होंने
    0.45
     *)&
    0.42
    B
    0.42
     Fink
    0.42
     Bhatt
    0.42
     Cil
    0.41
     Instrument
    0.41
    ад
    0.40
     аны
    0.40
    Activations Density 0.020%

    No Known Activations