© 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. 238702
    Prev
    Next
    INDEX
    Explanations

    mobile games and CVs

    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
    祈
    0.50
    incia
    0.50
    肚
    0.49
    য়ো
    0.48
    仍
    0.48
     POSITION
    0.48
    rzy
    0.47
     位
    0.47
     若
    0.47
    ieli
    0.46
    POSITIVE LOGITS
    getPassword
    0.54
    ต่อ
    0.52
    Consec
    0.49
    absorbed
    0.48
     IGF
    0.47
    coupling
    0.46
    แข็ง
    0.46
     continuum
    0.44
    Amaz
    0.44
    黴
    0.44
    Activations Density 0.000%

    No Known Activations