© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8573
    Prev
    Next
    INDEX
    Explanations

    Such a followed by adjective

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

    As such,

    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_40_width_16k_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
     intimated
    0.50
     inclined
    0.46
     dépass
    0.44
    ahas
    0.44
     intang
    0.43
    スマス
    0.43
    超過
    0.42
    "_
    0.42
     நே
    0.41
     necessitated
    0.40
    POSITIVE LOGITS
     Mall
    0.44
     Given
    0.40
     Truth
    0.40
    Truth
    0.39
    Owl
    0.39
    Glen
    0.38
     Few
    0.38
    elje
    0.38
     Among
    0.38
     Reel
    0.38
    Activations Density 0.056%

    No Known Activations