© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1816
    Prev
    Next
    INDEX
    Explanations

    qualifications and considerations

    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_40_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
    .
    0.17
    er
    0.16
     )
    0.15
    :
    0.15
    -->
    0.15
    _,
    0.15
    ?,
    0.15
    *,
    0.15
     -->
    0.15
     använder
    0.15
    POSITIVE LOGITS
     respect
    0.29
     regard
    0.29
     impunity
    0.28
     regards
    0.28
     emphasis
    0.26
    standing
    0.26
     énfasis
    0.26
     gusto
    0.26
     caveats
    0.25
     implications
    0.24
    Activations Density 0.162%

    No Known Activations