© 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. 15896
    Prev
    Next
    INDEX
    Explanations

    code `]` `)` `.`

    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
     
    0.57
    AP
    0.42
     pubblic
    0.42
    参考に
    0.42
     și
    0.41
    0
    0.41
     більше
    0.41
    骓
    0.41
    public
    0.40
     və
    0.39
    POSITIVE LOGITS
     မိ
    0.60
    ار
    0.48
     उदाहरण
    0.47
     stimul
    0.46
    ါ
    0.46
     inhalation
    0.46
     pints
    0.44
     toning
    0.44
    飥
    0.44
    parsedBlock
    0.44
    Activations Density 0.001%

    No Known Activations