© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120446
    Prev
    Next
    INDEX
    Explanations

    Blueprint visual scripting

    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_16_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
    c
    1.45
    ية
    1.34
    s
    1.27
    f
    1.26
    л
    1.19
    г
    1.19
    h
    1.18
    é
    1.16
    í
    1.16
    l
    1.12
    POSITIVE LOGITS
    ;
    1.13
    entially
    0.82
    edly
    0.80
    >
    0.80
    很
    0.80
    bera
    0.79
    ம்
    0.79
    ures
    0.77
    iosa
    0.76
    rians
    0.75
    Activations Density 0.001%

    No Known Activations