© 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-16K
    7. 541
    Prev
    Next
    INDEX
    Explanations

    countries, GB, W, m, mins

    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_16k_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
     ->
    0.25
     also
    0.24
    0.24
     =
    0.23
     is
    0.22
    波动
    0.22
     >=
    0.22
     B
    0.22
     x
    0.22
     euclidean
    0.22
    POSITIVE LOGITS
    й
    0.29
    у
    0.27
     మంది
    0.26
    adilan
    0.26
    اديم
    0.26
    на
    0.25
    మంది
    0.24
     miljoen
    0.24
    ْد
    0.24
     (!)
    0.23
    Activations Density 0.329%

    No Known Activations