© 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-65K
    4. 17228
    Prev
    Next
    INDEX
    Explanations

    specific terms followed by description

    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_65k_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
    $).
    0.42
    ]}
    0.37
     때문
    0.37
     tiež
    0.37
    挙げ
    0.37
    乒
    0.37
    ח
    0.36
     Khar
    0.36
     Belief
    0.36
    ])){
    0.36
    POSITIVE LOGITS
    angelo
    0.43
    шкой
    0.42
     glows
    0.41
     wouldn
    0.40
     extérieur
    0.39
     bodice
    0.39
    高品質
    0.38
     polyamide
    0.38
    phone
    0.38
    pe
    0.38
    Activations Density 0.001%

    No Known Activations