© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 220199
    Prev
    Next
    INDEX
    Explanations

    services, education, weekend, notes

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

    catalog files, agents, GMP, narrative, WebDriver, flutter

    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
     wich
    0.56
    phol
    0.49
    </em>
    0.49
     to
    0.49
     exemplify
    0.49
    </strong>
    0.47
     vere
    0.47
     palpable
    0.47
     optionally
    0.46
     residences
    0.46
    POSITIVE LOGITS
    ﻒ
    0.54
    ਰ
    0.51
    Beef
    0.49
    ूब
    0.49
    ور
    0.47
    ੋਰ
    0.45
     الجديد
    0.44
    ینگ
    0.44
    कान
    0.44
    فك
    0.44
    Activations Density 0.000%

    No Known Activations