© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 7838
    Prev
    Next
    INDEX
    Explanations

    information, resources, 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_65k_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
    膂
    0.41
    輋
    0.38
     myös
    0.38
    也很
    0.36
    インド
    0.36
     vendredi
    0.36
     ritmo
    0.35
     және
    0.35
     खासा
    0.35
     auffi
    0.34
    POSITIVE LOGITS
    ion
    0.37
    ()
    0.36
    iol
    0.35
    之类的
    0.35
    ())
    0.33
    r
    0.33
    ("")
    0.33
    ul
    0.32
    ru
    0.32
    ad
    0.32
    Activations Density 0.133%

    No Known Activations