© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    separators or alternatives

    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
     waarmee
    0.26
    $\,.
    0.25
     گی۔
    0.25
     wobei
    0.24
     دیا۔
    0.24
     گیا۔
    0.23
     گئے۔
    0.23
    ങ്ങളും
    0.22
    )”.
    0.22
     そして
    0.22
    POSITIVE LOGITS
     thì
    0.41
    ،
    0.38
    ，
    0.36
    ,
    0.35
    则
    0.34
    ၊
    0.32
    那就
    0.31
    [,]
    0.31
    則
    0.31
     maka
    0.30
    Activations Density 0.284%

    No Known Activations