© 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. 26704
    Prev
    Next
    INDEX
    Explanations

    roles, technical terms, tools

    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
    LE
    0.48
            
    0.46
     angepasst
    0.45
    CH
    0.43
     =,
    0.42
    <unused19>
    0.41
    ANEOUS
    0.41
     👌
    0.41
    Section
    0.41
     👇
    0.41
    POSITIVE LOGITS
    mounting
    0.48
    heet
    0.48
     választ
    0.47
    鎭
    0.46
    bu
    0.46
    nên
    0.46
    ᓲ
    0.45
    ку
    0.45
    মেজ
    0.45
    osof
    0.44
    Activations Density 0.000%

    No Known Activations