© 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. 111469
    Prev
    Next
    INDEX
    Explanations

    established, gaining, successfully

    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
     denaturation
    0.48
     surgeries
    0.43
     distortion
    0.40
     marshes
    0.40
     explorer
    0.39
     polarization
    0.39
    ⴷ
    0.39
     ഇത്തരം
    0.38
     surgery
    0.38
     ministries
    0.37
    POSITIVE LOGITS
     внима
    0.42
    ate
    0.39
    aten
    0.39
    اض
    0.39
     व्य
    0.38
     בי
    0.38
    ile
    0.38
     🙏
    0.38
     ле
    0.37
     семи
    0.37
    Activations Density 0.000%

    No Known Activations