© 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. 15161
    Prev
    Next
    INDEX
    Explanations

    closings like thanks or best

    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
    😍😍
    0.33
     גם
    0.33
     tambien
    0.33
    畱
    0.32
     también
    0.32
     entsprechende
    0.32
    <unused2173>
    0.31
     availed
    0.31
     आगे
    0.30
     також
    0.30
    POSITIVE LOGITS
    °,
    0.37
    **,
    0.36
    *,
    0.35
    ’,
    0.34
    ன்
    0.33
    faire
    0.32
    帧
    0.32
    $,
    0.32
    define
    0.30
    noise
    0.30
    Activations Density 0.016%

    No Known Activations