© 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. 29873
    Prev
    Next
    INDEX
    Explanations

    physics break

    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
     Kindern
    0.44
     دي
    0.43
    لاسه
    0.41
    柢
    0.41
    ificent
    0.41
    си
    0.41
     අනුව
    0.41
    തല്ല
    0.40
     paragra
    0.40
    obacter
    0.40
    POSITIVE LOGITS
    良い
    0.46
    కొ
    0.46
    Dp
    0.46
    ॉट
    0.44
    淹
    0.41
    दायक
    0.41
     RESEARCH
    0.40
     ఉంది
    0.39
     ca
    0.39
     বুক
    0.38
    Activations Density 0.009%

    No Known Activations