© 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. 41698
    Prev
    Next
    INDEX
    Explanations

    "one-point perspective"

    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
    self
    0.46
    '
    0.46
    p
    0.44
    प्पू
    0.43
    separation
    0.42
     पैर
    0.42
    person
    0.41
    AND
    0.39
    גם
    0.39
     alloy
    0.38
    POSITIVE LOGITS
    птова
    0.49
     кора
    0.47
    icherweise
    0.46
     betroffen
    0.46
    尬
    0.46
     آذ
    0.45
     universes
    0.45
    剌
    0.44
     relativamente
    0.43
     جامعة
    0.43
    Activations Density 0.001%

    No Known Activations