© 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. 104037
    Prev
    Next
    INDEX
    Explanations

    globe, globes

    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
     a
    1.34
    us
    1.17
    る
    1.10
    ul
    1.09
    ,
    1.07
    ল
    1.02
    usse
    1.02
    ac
    0.99
    ur
    0.97
    s
    0.97
    POSITIVE LOGITS
     Globe
    1.30
    N
    1.27
    T
    1.26
    L
    1.16
    S
    1.15
    U
    1.13
    K
    1.10
    য়া
    1.09
     globe
    1.08
    ান্তরে
    1.08
    Activations Density 0.004%

    No Known Activations