© 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. 170100
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    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
    ской
    0.57
    ంలోని
    0.52
    ⇓
    0.49
    ProguardFile
    0.49
     informática
    0.48
     pengaturan
    0.47
     aproximadamente
    0.47
    odora
    0.47
    údio
    0.46
    ახ
    0.46
    POSITIVE LOGITS
    I
    0.50
    Бо
    0.46
    Rec
    0.43
    Timer
    0.43
    Courtesy
    0.43
    内心
    0.43
    Gi
    0.43
    Avec
    0.42
    With
    0.42
    DIS
    0.42
    Activations Density 0.001%

    No Known Activations