© 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. 8513
    Prev
    Next
    INDEX
    Explanations

    hacking and camping tips

    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
     NUE
    0.50
     faç
    0.50
     ת
    0.49
    últ
    0.47
    íj
    0.47
    '
    0.47
     הת
    0.46
    наче
    0.44
    િસ
    0.44
     GAME
    0.44
    POSITIVE LOGITS
    golang
    0.58
     semisimple
    0.55
     enthal
    0.48
     resonated
    0.47
    ₚ
    0.46
     symplect
    0.46
     integrable
    0.46
    uterine
    0.46
    openzeppelin
    0.46
     stirred
    0.45
    Activations Density 0.002%

    No Known Activations