© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 196425
    Prev
    Next
    INDEX
    Explanations

    panoramic setting

    np_acts-logits-general · gemini-2.5-flash-lite

    analysis, transformation, differentiable augmentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Inser
    0.52
    に対し
    0.47
     위치
    0.47
     მი
    0.46
    グリ
    0.46
     напи
    0.45
    FullName
    0.45
    徳
    0.45
    <unused723>
    0.45
    ᠣ
    0.44
    POSITIVE LOGITS
     paise
    0.47
     précédentes
    0.41
     Bhajan
    0.41
     of
    0.41
    拨款
    0.40
     beginnetje
    0.40
    चार
    0.39
     hopelessly
    0.39
     précédents
    0.39
    știg
    0.39
    Activations Density 0.001%

    No Known Activations