© 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. 74685
    Prev
    Next
    INDEX
    Explanations

    Gemini model

    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
    Negative Logits
     உம்
    0.51
    𝘢
    0.51
    et
    0.49
    noDB
    0.48
    ęła
    0.47
    गंज
    0.47
    గు
    0.46
    ᴀ
    0.46
    𝘦
    0.46
    StoredKeys
    0.46
    POSITIVE LOGITS
     variants
    0.44
     as
    0.43
    variants
    0.43
     scalar
    0.42
     trader
    0.41
     screams
    0.41
     consensual
    0.41
     by
    0.41
     remarquable
    0.41
     neod
    0.41
    Activations Density 0.002%

    No Known Activations