© 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-65K
    7. 56460
    Prev
    Next
    INDEX
    Explanations

    Identify Situation

    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_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
     RH
    0.46
     adored
    0.44
    а
    0.44
     руководство
    0.43
    мента
    0.42
     devoted
    0.42
     drew
    0.42
    се
    0.42
     beloved
    0.42
     tormented
    0.41
    POSITIVE LOGITS
    ulint
    0.49
     kapp
    0.48
    ロッパ
    0.45
    ahme
    0.44
    Verb
    0.44
     লাগিয়ে
    0.44
    ዣ
    0.44
     økonom
    0.43
    竑
    0.43
    Unter
    0.42
    Activations Density 0.005%

    No Known Activations