© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 165026
    Prev
    Next
    INDEX
    Explanations

    host machine

    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
    附件
    0.41
    Attachments
    0.39
    ಸ
    0.39
    Battle
    0.39
    Rational
    0.39
    Unique
    0.38
    וד
    0.37
    Huawei
    0.37
    Sine
    0.36
     మాట్లాడుతూ
    0.36
    POSITIVE LOGITS
     Rept
    0.42
     indign
    0.42
     市
    0.41
     getContent
    0.41
    娱
    0.41
     دین
    0.40
     Noct
    0.39
     repres
    0.39
     hồ
    0.38
     entertain
    0.38
    Activations Density 0.003%

    No Known Activations