© 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. 31-GEMMASCOPE-2-RES-262K
    7. 13790
    Prev
    Next
    INDEX
    Explanations

    self, not, if, capital, slumber

    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
    UTHERN
    0.49
    سباب
    0.48
    厩
    0.45
    ទ្
    0.45
     aerobics
    0.44
     coords
    0.44
    rlen
    0.43
    ernsey
    0.42
     作業
    0.42
     প্যাকে
    0.42
    POSITIVE LOGITS
    ні
    0.59
    。
    0.51
    дні
    0.49
    ită
    0.47
    ді
    0.47
    ิ
    0.45
     domanda
    0.45
    หรือ
    0.44
    ισ
    0.44
    ोत्
    0.44
    Activations Density 0.001%

    No Known Activations