© 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-262K
    4. 28376
    Prev
    Next
    INDEX
    Explanations

    find specific content

    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
     (!
    0.48
    。(
    0.47
    㢼
    0.46
     (!)
    0.44
     विधे
    0.42
    (!
    0.42
     напи
    0.42
     that
    0.41
     파
    0.40
     habitually
    0.40
    POSITIVE LOGITS
    ক্টর
    0.42
    ចំនួន
    0.40
    acara
    0.40
    assadors
    0.40
    வர்களாக
    0.39
    Ec
    0.39
    claw
    0.39
     oligos
    0.39
    अच्छ
    0.38
    กระจ
    0.38
    Activations Density 0.005%

    No Known Activations