Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 2474
    Prev
    Next
    INDEX
    Explanations

    out with or out of

    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_53_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
    из
    0.58
     Außen
    0.53
    ออก
    0.52
    출
    0.51
     outward
    0.49
    외
    0.49
     из
    0.49
    ອອກ
    0.47
    Outside
    0.47
     outside
    0.46
    POSITIVE LOGITS
    ting
    0.69
    ted
    0.68
    TING
    0.59
    ters
    0.58
    पुट
    0.54
    TINGS
    0.50
    팅
    0.49
    chea
    0.47
     loud
    0.46
    liers
    0.46
    Activations Density 0.113%

    No Known Activations