© 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. 40-GEMMASCOPE-2-RES-262K
    7. 20871
    Prev
    Next
    INDEX
    Explanations

    letting you know

    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_40_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
     đòi
    0.51
     fucking
    0.43
    できる
    0.43
     demands
    0.42
     arrog
    0.42
    要求
    0.42
     nigga
    0.41
    </html>
    0.41
    십니까
    0.40
     IGBT
    0.40
    POSITIVE LOGITS
     kiddos
    0.59
     linens
    0.56
     lovely
    0.54
    덬
    0.52
     habitudes
    0.52
     bridal
    0.50
     Oogie
    0.49
     gorgeous
    0.48
    lovely
    0.48
     fates
    0.47
    Activations Density 0.001%

    No Known Activations