© 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. 76654
    Prev
    Next
    INDEX
    Explanations

    experts, analyst, without, Limit

    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
     fattori
    0.59
     ipotesi
    0.59
     pouces
    0.55
    Ҥ
    0.54
     ወይም
    0.53
     silam
    0.53
    隐含规则
    0.53
     방식으로
    0.53
     frågor
    0.52
    职称
    0.52
    POSITIVE LOGITS
    a
    0.55
    y
    0.52
    z
    0.50
    d
    0.47
    et
    0.46
    f
    0.46
    be
    0.44
    it
    0.43
    land
    0.43
    ta
    0.42
    Activations Density 0.001%

    No Known Activations