© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    integer variables and data fields

    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
     पाण्याच्या
    0.19
    िक
    0.19
    प
    0.17
     abordagem
    0.17
    तून
    0.17
    肿瘤
    0.16
    敕
    0.16
    URNIZOR
    0.16
     Unis
    0.16
    ్రమ
    0.16
    POSITIVE LOGITS
    name
    0.21
    key
    0.19
     clazz
    0.19
     _
    0.18
    is
    0.18
     x
    0.18
     ethnicity
    0.18
     key
    0.18
     username
    0.18
     baseHP
    0.18
    Activations Density 0.180%

    No Known Activations