© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 111374
    Prev
    Next
    INDEX
    Explanations

    potentially extend or lead

    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
    爯
    0.43
     заболе
    0.42
     монет
    0.41
    ヲ
    0.41
    лакти
    0.40
    ቆ
    0.38
     Brush
    0.38
     мини
    0.38
    绷
    0.38
    ጌ
    0.37
    POSITIVE LOGITS
    貽
    0.46
    ificare
    0.41
    ivid
    0.40
    imodal
    0.40
    heri
    0.38
     добиться
    0.38
    Afghanistan
    0.37
     Pob
    0.37
    anse
    0.37
    contrast
    0.37
    Activations Density 0.002%

    No Known Activations