© 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. 126592
    Prev
    Next
    INDEX
    Explanations

    detective mystery genres

    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
    Об
    0.48
    Este
    0.46
    关于
    0.45
     Lerner
    0.45
    Questo
    0.44
    Esto
    0.43
    この
    0.43
    s
    0.42
    Esta
    0.42
    ್
    0.42
    POSITIVE LOGITS
    acy
    0.47
    日数
    0.46
     صحی
    0.44
    ancos
    0.44
     psychosocial
    0.44
     diversité
    0.43
     révol
    0.43
     فلسطینی
    0.43
    indeer
    0.42
    azir
    0.42
    Activations Density 0.000%

    No Known Activations