© 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. 99621
    Prev
    Next
    INDEX
    Explanations

    first, stubborn, will, days, of, I, screw, the, IP

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

    understanding concepts and variations

    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
    نامہ
    0.44
    🏕
    0.44
    десь
    0.43
     Anakin
    0.43
     നമഃ
    0.41
    สมาชิก
    0.41
    잭
    0.40
    帅
    0.39
    lamualaikum
    0.39
     dici
    0.38
    POSITIVE LOGITS
    ("&
    0.47
     Ô
    0.43
     पुढे
    0.43
    fat
    0.42
     amplitudes
    0.42
    parseFloat
    0.42
    bore
    0.42
     തുട
    0.41
     suspensions
    0.41
     പരാ
    0.41
    Activations Density 0.001%

    No Known Activations