© 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. 9118
    Prev
    Next
    INDEX
    Explanations

    suppliers, specifications, players

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

    file paths and programming code

    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
    шчы
    0.41
    Appl
    0.38
    Là
    0.36
    Straße
    0.35
    ♛
    0.35
    сё
    0.35
    Successful
    0.35
    Batt
    0.35
     begann
    0.34
    Were
    0.34
    POSITIVE LOGITS
     утро
    0.43
    িয়োগ
    0.40
    ద్ధి
    0.40
     quantos
    0.39
    故障
    0.38
    ುತ್ತೇವೆ
    0.38
    icznego
    0.38
    cursos
    0.38
    <unused82>
    0.37
     mely
    0.36
    Activations Density 0.161%

    No Known Activations