© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27225
    Prev
    Next
    INDEX
    Explanations

    interval training

    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_16_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
    ad
    0.50
    čiai
    0.47
    घाडी
    0.43
    ી
    0.43
    aerial
    0.42
    i
    0.41
    d
    0.41
    lebihan
    0.40
    difficulty
    0.40
    really
    0.38
    POSITIVE LOGITS
    IL
    0.46
    '
    0.45
    س
    0.44
    IDA
    0.43
     trat
    0.43
     sprint
    0.43
     regres
    0.41
    وان
    0.40
     trabal
    0.40
    ാൻ
    0.40
    Activations Density 0.001%

    No Known Activations