© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    finite approximations

    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
     TOEFL
    0.43
    ానికి
    0.40
    manufacturing
    0.40
    才能
    0.39
    ません
    0.39
     চীনে
    0.39
    dnn
    0.39
    若
    0.38
    正月
    0.38
    선
    0.38
    POSITIVE LOGITS
     stabilized
    0.45
     stabilize
    0.44
     стабили
    0.44
     pivoted
    0.43
     symmetric
    0.43
     meaningfully
    0.42
     regra
    0.42
     नियंत्रित
    0.40
     swirling
    0.40
     symmetry
    0.40
    Activations Density 0.001%

    No Known Activations