© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86067
    Prev
    Next
    INDEX
    Explanations

    winning and giveaway campaigns

    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_16_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
    Steam
    0.58
    蟶
    0.56
    ائح
    0.55
     VLC
    0.55
     Também
    0.54
     Steam
    0.54
     Lég
    0.54
     zahlen
    0.54
    善
    0.53
    தமான
    0.52
    POSITIVE LOGITS
     prize
    0.60
     प्रतियोगिता
    0.57
    ଜ
    0.53
     konkurs
    0.52
    unter
    0.52
    AMINATION
    0.49
     розы
    0.48
     \
    0.48
    ne
    0.48
    ighter
    0.48
    Activations Density 0.006%

    No Known Activations