© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    mission statements and documentation

    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
     naph
    0.45
    </tfoot>
    0.42
     spectrometers
    0.42
     sacrificed
    0.42
     stallions
    0.41
     sly
    0.41
     erythrocytes
    0.41
     moieties
    0.41
     residues
    0.40
    ರವಾಗಿ
    0.40
    POSITIVE LOGITS
    relse
    0.41
     पु
    0.39
     デ
    0.39
    デ
    0.38
    ﾀ
    0.37
     टे
    0.37
    娅
    0.37
    pu
    0.37
     Administrat
    0.37
     Plot
    0.37
    Activations Density 0.002%

    No Known Activations