© 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. 50755
    Prev
    Next
    INDEX
    Explanations

    requiring more of the same

    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
     on
    0.53
    と
    0.42
    то
    0.42
    谈
    0.41
     Sở
    0.41
     Mental
    0.40
     CAPITAL
    0.40
    の
    0.39
    鰱
    0.39
    ની
    0.39
    POSITIVE LOGITS
     laug
    0.48
     etanol
    0.47
     alegria
    0.46
    stil
    0.45
     esport
    0.45
    stos
    0.45
    .$
    0.45
     συνεχ
    0.44
    ளுடன்
    0.44
    هما
    0.44
    Activations Density 0.001%

    No Known Activations