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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 17797
    Prev
    Next
    INDEX
    Explanations

    comma separated lists

    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
     Boyfriend
    0.45
    boyfriend
    0.43
    ッキリ
    0.42
    ifaiFace
    0.41
    帑
    0.40
     दांत
    0.40
    waffe
    0.40
    峼
    0.40
     UnwrapRef
    0.39
    崠
    0.39
    POSITIVE LOGITS
     comma
    1.40
     separated
    1.27
    Comma
    1.23
    comma
    1.21
    separated
    1.18
     commas
    1.15
     separator
    1.14
     separators
    1.08
     semicolon
    1.05
    Separ
    0.99
    Activations Density 0.047%

    No Known Activations