© 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. 210464
    Prev
    Next
    INDEX
    Explanations

    language comprehension and generation

    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
    idest
    0.41
    ципа
    0.40
    蒌
    0.40
     Prend
    0.38
     recomienda
    0.38
     entiende
    0.38
    訒
    0.38
     Nuestro
    0.37
     nostre
    0.37
     എന്റെ
    0.36
    POSITIVE LOGITS
     ሙ
    0.38
     পিলার
    0.37
    ån
    0.36
     จน
    0.36
     অস্থির
    0.35
    lieu
    0.35
    撲
    0.35
     linearly
    0.35
    Structural
    0.35
    疣
    0.34
    Activations Density 0.000%

    No Known Activations