© 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. 20260
    Prev
    Next
    INDEX
    Explanations

    identifying your triggers

    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
    3
    0.45
    Rusty
    0.43
    Apache
    0.42
     enlarge
    0.42
     حی
    0.42
    4
    0.41
    state
    0.41
    dead
    0.41
     الحي
    0.41
     குடிய
    0.40
    POSITIVE LOGITS
    ལ་
    0.47
    vrir
    0.41
     Contrary
    0.41
    íbrio
    0.41
    lichkeiten
    0.41
     النصوص
    0.41
     Fare
    0.39
     suing
    0.39
     /{
    0.39
    ಿಸಿ
    0.39
    Activations Density 0.002%

    No Known Activations