© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13043
    Prev
    Next
    INDEX
    Explanations

    `using`, `conversion`, `conflict`, `publish`

    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
    Negative Logits
     turut
    0.43
     ikut
    0.42
    BIUM
    0.41
    ongono
    0.40
     skillet
    0.40
    ’
    0.40
     masque
    0.39
    ázej
    0.39
    '
    0.39
    arl
    0.39
    POSITIVE LOGITS
    ｔ
    0.43
    ᠶ
    0.42
    𝒞
    0.40
     exiled
    0.40
    來說
    0.39
    Ling
    0.39
    ുവരി
    0.38
    🦊
    0.38
    Pes
    0.38
     interpreting
    0.37
    Activations Density 0.119%

    No Known Activations