© 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. 84747
    Prev
    Next
    INDEX
    Explanations

    exploring dark themes

    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
     favorably
    0.52
    ﻤ
    0.49
     enforce
    0.47
     reorganize
    0.47
    रा
    0.46
     approve
    0.46
     encontra
    0.46
     стар
    0.45
     graciously
    0.45
     favorable
    0.45
    POSITIVE LOGITS
    หรือ
    0.44
    හර
    0.44
    ಥವಾ
    0.43
    uter
    0.43
     ወይም
    0.43
    াইয়৷
    0.43
    iy
    0.42
    phone
    0.42
    javax
    0.42
    ard
    0.42
    Activations Density 0.014%

    No Known Activations