© 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. 17512
    Prev
    Next
    INDEX
    Explanations

    Args: encryption, file, path, key

    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
     خور
    0.43
    łeś
    0.43
    subtype
    0.41
    ourd
    0.41
    LLER
    0.41
    UPS
    0.40
    冠
    0.40
    덬
    0.40
    Unavailable
    0.39
     legitim
    0.39
    POSITIVE LOGITS
     зді
    0.43
     Bangor
    0.42
    եմ
    0.41
     repealed
    0.40
    íns
    0.40
     గత
    0.40
     норма
    0.39
     Regulatory
    0.39
     दोन्ही
    0.39
     এতদিন
    0.39
    Activations Density 0.000%

    No Known Activations