© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43197
    Prev
    Next
    INDEX
    Explanations

    acknowledging, assembling, total, fabric, technically

    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
     सलाह
    0.52
     égard
    0.50
     seide
    0.49
     आहे
    0.48
    ဤ
    0.47
     मध्ये
    0.46
     współpracy
    0.46
     εργ
    0.46
     योज
    0.46
    Dalam
    0.46
    POSITIVE LOGITS
    u
    0.46
     tabulation
    0.44
    散
    0.43
     повин
    0.42
    n
    0.42
     bí
    0.42
     studente
    0.41
    char
    0.40
     králov
    0.40
     banca
    0.40
    Activations Density 0.003%

    No Known Activations