© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    HTML class attribute usage

    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
    t
    1.65
    d
    1.34
    g
    1.27
    c
    1.26
    s
    1.23
    ,
    1.20
    u
    1.13
    i
    1.07
    z
    1.05
    di
    1.02
    POSITIVE LOGITS
    1.64
    ва
    1.41
    ა
    1.33
    ни
    1.29
    ام
    1.22
    า
    1.22
    ्य
    1.20
    са
    1.20
    та
    1.20
    ного
    1.19
    Activations Density 0.010%

    No Known Activations