© 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. 31-GEMMASCOPE-2-RES-262K
    7. 55120
    Prev
    Next
    INDEX
    Explanations

    automatically, log, delete, subtle, bit

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Bigg
    0.50
    酈
    0.47
    Knight
    0.46
    Novo
    0.45
    न
    0.45
    ɴ
    0.45
    Архі
    0.44
    𝓷
    0.44
    сів
    0.44
    ไหน
    0.43
    POSITIVE LOGITS
     $
    0.47
     scont
    0.44
    悄
    0.43
    🤫
    0.42
    $
    0.41
     determinante
    0.41
     clandestine
    0.40
     مباراة
    0.39
     secreto
    0.39
     sly
    0.39
    Activations Density 0.000%

    No Known Activations