© 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. 24415
    Prev
    Next
    INDEX
    Explanations

    comparisons

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

    digital preservation and identity

    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
    olaire
    0.46
     -.
    0.42
    lds
    0.42
    ledu
    0.42
    ksjon
    0.42
    ki
    0.41
     κι
    0.41
    cheduling
    0.40
    ابقة
    0.40
     végétale
    0.39
    POSITIVE LOGITS
    𝐒
    0.53
    ЕН
    0.50
    лом
    0.48
    ТР
    0.47
    शील
    0.46
     impair
    0.45
    OBJECT
    0.45
    CCA
    0.45
     nghiêm
    0.45
    ТЕ
    0.45
    Activations Density 0.000%

    No Known Activations