© 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. 37207
    Prev
    Next
    INDEX
    Explanations

    describes the subject

    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
     nedeniyle
    0.46
    ή
    0.43
    PI
    0.43
    டியில்
    0.43
     அதிசயங்கள்
    0.42
    细节
    0.41
     with
    0.41
     由于
    0.41
     लिखकर
    0.41
     کرکے
    0.40
    POSITIVE LOGITS
     diventare
    0.48
     unparalleled
    0.48
     inevitable
    0.47
    不仅仅
    0.46
     inability
    0.46
     unbearable
    0.46
    ᡵ
    0.46
    成為
    0.45
     irresistible
    0.45
     нередко
    0.45
    Activations Density 0.072%

    No Known Activations