© 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. 120804
    Prev
    Next
    INDEX
    Explanations

    signing up, performance, come here, DBA, pay

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

    custom ROM, invasive endoscopic, leap seconds

    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
     sowing
    0.52
     repurchase
    0.48
    ϙ
    0.48
    醝
    0.48
     Repert
    0.47
     meanings
    0.47
    rok
    0.46
     exons
    0.46
    䩕
    0.46
    어서
    0.46
    POSITIVE LOGITS
     de
    0.47
    Thomas
    0.46
    de
    0.45
     Thomas
    0.44
    t
    0.44
     پایین
    0.43
    f
    0.43
     Hutchinson
    0.43
    Nurse
    0.42
    Saint
    0.42
    Activations Density 0.000%

    No Known Activations