© 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. 10693
    Prev
    Next
    INDEX
    Explanations

    February exercise Game Bar Hard skills

    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
    entingan
    0.52
    ۴
    0.50
    cieron
    0.49
     hauteur
    0.48
    łek
    0.48
     Bumi
    0.47
     упа
    0.47
    पण
    0.47
    椂
    0.47
    aa
    0.46
    POSITIVE LOGITS
     chemists
    0.48
     therapists
    0.48
     compressors
    0.47
     oscillators
    0.47
     tacos
    0.46
     plumbers
    0.46
     administrators
    0.46
     musicians
    0.46
     clinicians
    0.45
     sliders
    0.45
    Activations Density 0.002%

    No Known Activations