© 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. 62137
    Prev
    Next
    INDEX
    Explanations

    suffers harm

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

    Teoría de la Correspondencia

    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
    িন্দু
    0.49
     θερ
    0.47
    ự
    0.46
     дан
    0.43
    executeUpdate
    0.43
    detectChanges
    0.43
    皱
    0.42
    ôle
    0.42
    运输
    0.42
     लवली
    0.42
    POSITIVE LOGITS
    ",
    0.51
    !",
    0.49
    "(
    0.48
    0.47
     Recommended
    0.47
     Therapie
    0.46
     Material
    0.46
     材質
    0.46
     själ
    0.45
     Minimalism
    0.45
    Activations Density 0.000%

    No Known Activations