© 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. 8560
    Prev
    Next
    INDEX
    Explanations

    already have

    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
     вновь
    0.35
    越多
    0.35
     生命周期
    0.34
    痹
    0.34
    闾
    0.34
    রো
    0.33
    曜
    0.33
    ể
    0.33
    再度
    0.32
    మ్
    0.32
    POSITIVE LOGITS
     already
    2.47
     Already
    2.20
    already
    2.16
    Already
    2.13
     уже
    2.08
     ऑलरेडी
    2.08
     allerede
    2.00
     już
    1.89
     bereits
    1.87
     redan
    1.80
    Activations Density 0.392%

    No Known Activations