© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120599
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and continuations

    np_acts-logits-general · gemini-2.5-flash-lite

    LinkedIn Articles, Facebook Groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.50
    TV
    0.47
    pp
    0.46
    ↵↵
    0.46
    chim
    0.46
     Superior
    0.46
    coded
    0.45
    ADN
    0.45
    Stock
    0.45
    LA
    0.44
    POSITIVE LOGITS
    ränkt
    0.55
     플
    0.52
    ánea
    0.51
    ᙱ
    0.50
    啭
    0.50
     فراموش
    0.49
    oconvex
    0.49
    ీయ
    0.49
    బడు
    0.49
    endlich
    0.49
    Activations Density 0.000%

    No Known Activations