© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119282
    Prev
    Next
    INDEX
    Explanations

    allowed or permitted

    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_40_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
    謦
    0.52
    隐含
    0.42
     nud
    0.41
     subsidy
    0.40
    ็ก
    0.39
     nudge
    0.38
     patron
    0.38
     chords
    0.38
     golf
    0.38
    meld
    0.38
    POSITIVE LOGITS
    Pakistan
    0.40
    วัน
    0.39
     deň
    0.38
     समुच्चय
    0.37
    톈
    0.37
     Transl
    0.37
     פע
    0.37
     células
    0.36
    ohama
    0.36
     сутки
    0.36
    Activations Density 0.001%

    No Known Activations