© 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. 9306
    Prev
    Next
    INDEX
    Explanations

    cell phone jammer blocker

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

    list formatting and punctuation

    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
    コレート
    0.52
     cytologic
    0.48
     secteurs
    0.43
    َنْ
    0.43
    GONDOR
    0.43
    کومت
    0.43
     precession
    0.42
     الدراسة
    0.41
    LETIN
    0.41
     உலோக
    0.41
    POSITIVE LOGITS
    al
    0.48
     is
    0.42
     J
    0.41
     Do
    0.40
     Autom
    0.40
     R
    0.40
    esi
    0.40
    Autom
    0.40
     Three
    0.40
     Only
    0.40
    Activations Density 0.066%

    No Known Activations