© 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. 41492
    Prev
    Next
    INDEX
    Explanations

    lists and bullet points

    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
     Kurz
    0.47
    ن
    0.46
     thorns
    0.45
     stoneware
    0.44
    }+\
    0.43
     луч
    0.43
     pique
    0.43
     Mediation
    0.42
    目前的
    0.42
     LocalDate
    0.41
    POSITIVE LOGITS
    '')
    0.50
    '
    0.49
    :""
    0.45
    ses
    0.44
    des
    0.44
    sembles
    0.43
    secretary
    0.43
    duct
    0.42
    ۰
    0.42
    esthetics
    0.41
    Activations Density 0.001%

    No Known Activations