Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 29978
    Prev
    Next
    INDEX
    Explanations

    sex, renewable, RSA, gravity, PIL, key, support

    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
    ဟ
    0.42
    袠
    0.42
    ಂತ್ರ
    0.42
     ফি
    0.39
    नावश्यक
    0.39
     únicos
    0.38
    rophages
    0.38
    鋆
    0.38
    állítás
    0.38
    funcs
    0.37
    POSITIVE LOGITS
     komment
    0.43
     envy
    0.41
     freedom
    0.40
     കഴിഞ്ഞ
    0.39
     arrogance
    0.39
     midnight
    0.38
     wist
    0.38
     bath
    0.37
     gerne
    0.37
     size
    0.37
    Activations Density 0.000%

    No Known Activations