© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5333
    Prev
    Next
    INDEX
    Explanations

    numbered lists and rankings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     योज
    0.74
     actuators
    0.74
     Therapist
    0.73
    óle
    0.72
     primitives
    0.72
     activation
    0.70
    imitives
    0.69
    穌
    0.69
    注入
    0.68
    ავლ
    0.68
    POSITIVE LOGITS
     ranking
    3.56
     rankings
    3.53
     ranked
    3.34
     rank
    3.25
    Rank
    3.21
     Ranking
    3.17
    Ranking
    3.15
    ranking
    3.12
    ranked
    3.11
     Rankings
    3.06
    Activations Density 0.854%

    No Known Activations