© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 77026
    Prev
    Next
    INDEX
    Explanations

    protagonist, grimace, free entry

    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
    جا
    0.55
    т
    0.51
    ци
    0.47
    тэй
    0.46
    р
    0.46
    ت
    0.46
    håll
    0.46
    д
    0.45
    ه
    0.44
    スキー
    0.43
    POSITIVE LOGITS
    ning
    0.51
     চার
    0.48
    Development
    0.45
     पांच
    0.45
     სამ
    0.45
     mathematic
    0.45
    <0xBE>
    0.45
     Loeb
    0.44
     beg
    0.43
     sann
    0.42
    Activations Density 0.002%

    No Known Activations