© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 757
    Prev
    Next
    INDEX
    Explanations

    initial setup

    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_65k_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
     Linton
    0.33
     explanatory
    0.32
     policemen
    0.31
     ontstaan
    0.31
     phenomenon
    0.30
     ď
    0.30
     wikipagina
    0.29
     ina
    0.29
     explained
    0.29
     ẹ
    0.29
    POSITIVE LOGITS
    These
    0.40
    Эти
    0.36
    best
    0.35
    這些
    0.34
    可惜
    0.34
     लीड
    0.34
    謹
    0.34
    these
    0.33
    deps
    0.33
    더
    0.33
    Activations Density 0.207%

    No Known Activations