© 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. 79414
    Prev
    Next
    INDEX
    Explanations

    MUI, costs, want

    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
    ()
    0.40
    강
    0.39
     disco
    0.39
     there
    0.39
    -
    0.38
    max
    0.38
     Dublin
    0.38
    리
    0.38
    嘉
    0.38
     ireland
    0.37
    POSITIVE LOGITS
     vogliamo
    0.47
     хотим
    0.46
     приятно
    0.45
     ರೈ
    0.45
     invit
    0.44
     uitgen
    0.44
     CFRP
    0.44
     ನಿಮ್ಮ
    0.43
     queremos
    0.43
     przyjem
    0.43
    Activations Density 0.014%

    No Known Activations