© 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. 56527
    Prev
    Next
    INDEX
    Explanations

    choose or symbol

    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
    y
    0.47
    Garage
    0.45
    ump
    0.44
     гара
    0.44
    नाथन
    0.43
    พอ
    0.43
    ym
    0.42
    nań
    0.42
     कैटेगरी
    0.41
    Trader
    0.41
    POSITIVE LOGITS
    じた
    0.48
     Barcl
    0.47
    ਜ
    0.46
    に示す
    0.45
     Accesat
    0.44
     effectu
    0.43
    鉋
    0.43
     blandt
    0.43
     that
    0.42
     exhaust
    0.42
    Activations Density 0.010%

    No Known Activations