© 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. 25223
    Prev
    Next
    INDEX
    Explanations

    invading surrounding, inside the, beyond

    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
     portions
    0.51
     impetus
    0.50
    뿐
    0.48
     appell
    0.45
     parts
    0.44
     apel
    0.44
    적인
    0.44
    وازن
    0.43
     portion
    0.41
     responsibility
    0.41
    POSITIVE LOGITS
     `{
    0.49
    ᴴ
    0.44
    ަ
    0.44
    
    0.44
     стрель
    0.43
    <0x8B>
    0.43
    ☠
    0.43
     हमरे
    0.42
    ℍ
    0.42
     レン
    0.42
    Activations Density 0.000%

    No Known Activations