© 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. 17206
    Prev
    Next
    INDEX
    Explanations

    past papers and 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_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
    わかり
    0.48
    独自の
    0.47
    ಂತೆ
    0.45
    報告
    0.42
    純
    0.42
    縮
    0.41
    ましょう
    0.40
    邝
    0.40
    гда
    0.40
    鐩
    0.40
    POSITIVE LOGITS
    s
    0.70
     (
    0.55
    years
    0.49
    traffic
    0.47
    employees
    0.47
    smile
    0.47
     effectués
    0.46
     ਅਤੇ
    0.44
     (&
    0.44
    speed
    0.44
    Activations Density 0.000%

    No Known Activations