Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64901
    Prev
    Next
    INDEX
    Explanations

    Button, General Manager, cutscenes, /usr/

    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
     njia
    0.49
     SCGS
    0.49
     سپورت
    0.48
    jenigen
    0.48
     تاز
    0.47
     baratos
    0.47
     economici
    0.46
    Ꮏ
    0.46
     informasi
    0.46
    Ꮰ
    0.44
    POSITIVE LOGITS
    on
    0.55
     on
    0.50
    ö
    0.47
    ond
    0.46
    aría
    0.45
    àn
    0.43
     Insulation
    0.43
    show
    0.42
    à
    0.42
    ob
    0.41
    Activations Density 0.003%

    No Known Activations