© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76770
    Prev
    Next
    INDEX
    Explanations

    including elements

    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_31_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
    es
    0.48
    le
    0.43
    ass
    0.43
     dépens
    0.42
    d
    0.42
    ੨
    0.42
    ou
    0.41
    ate
    0.41
    ヨ
    0.40
    ent
    0.40
    POSITIVE LOGITS
     včetně
    0.49
     including
    0.47
    INCLUDING
    0.45
     کرمان
    0.44
     gratifying
    0.43
     inklusive
    0.43
     roof
    0.42
     alkalies
    0.42
     Three
    0.42
     thatched
    0.42
    Activations Density 0.003%

    No Known Activations