© 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. 39936
    Prev
    Next
    INDEX
    Explanations

    printing, families, contain, demonstrate

    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
     ملك
    0.52
    Sexo
    0.48
    implantation
    0.47
     ها
    0.44
     বিষ
    0.43
     တ
    0.43
    情報を
    0.43
    ("^
    0.43
     வீடியோ
    0.43
     ልጅ
    0.43
    POSITIVE LOGITS
    ād
    0.45
     thofe
    0.44
    ppins
    0.44
     Ministers
    0.42
     PHASE
    0.42
     INCLUDE
    0.40
     breathe
    0.40
     RIP
    0.40
    со
    0.40
     Roundup
    0.39
    Activations Density 0.003%

    No Known Activations