© 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. 76935
    Prev
    Next
    INDEX
    Explanations

    surprisingly sharp, lively, influences

    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
     رست
    0.47
     あ
    0.46
     assertThat
    0.45
     놀
    0.43
     便利
    0.42
    놀
    0.42
     رجسٹ
    0.42
     ए
    0.41
     vacaciones
    0.41
     임
    0.41
    POSITIVE LOGITS
    et
    0.50
    č
    0.47
     maximum
    0.47
    etan
    0.45
    leyen
    0.44
     στο
    0.42
     développ
    0.42
    ك
    0.42
    annte
    0.42
    ent
    0.42
    Activations Density 0.003%

    No Known Activations