© 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. 143702
    Prev
    Next
    INDEX
    Explanations

    "Would You Rather" questions

    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
     Ad
    0.41
    χε
    0.40
    篝
    0.39
     OEMs
    0.38
     ambienti
    0.38
     tribes
    0.38
    ющихся
    0.38
    olytic
    0.37
    としている
    0.37
    ཁ
    0.37
    POSITIVE LOGITS
    سٹم
    0.55
     calculator
    0.49
     ماشینونه
    0.48
    ornado
    0.48
    Landau
    0.48
     سوچ
    0.46
     story
    0.45
     لم
    0.45
     sentença
    0.45
     முற
    0.45
    Activations Density 0.008%

    No Known Activations