Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 211425
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and rates

    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
     explic
    0.37
    нодоро
    0.36
     дорогу
    0.36
    
    0.36
    若干
    0.35
     nho
    0.35
     несколь
    0.35
     അധിക
    0.35
    geqslant
    0.34
    iyu
    0.34
    POSITIVE LOGITS
     gevoel
    0.38
    ce
    0.37
    Feeling
    0.37
     Boo
    0.37
     слабо
    0.36
    ✬
    0.36
    familyName
    0.36
    teres
    0.35
    TEXT
    0.35
    сное
    0.35
    Activations Density 0.003%

    No Known Activations