© 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-65K
    7. 11861
    Prev
    Next
    INDEX
    Explanations

    a property holds

    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
    Ⅸ
    0.45
    IX
    0.44
    OTHER
    0.43
    OUTH
    0.42
    ❷
    0.42
    𝙱
    0.41
     ۳
    0.40
     OTHER
    0.40
    രുദ്ധ
    0.39
     TWO
    0.39
    POSITIVE LOGITS
    reiro
    0.39
    verbrauch
    0.39
    y
    0.39
     rallying
    0.38
     erklärt
    0.37
     prih
    0.36
     affirms
    0.35
     parlato
    0.35
     steckt
    0.35
     animating
    0.35
    Activations Density 0.005%

    No Known Activations