© 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. 26759
    Prev
    Next
    INDEX
    Explanations

    Google services, additional $, President Dwight, 1st flip, DC power

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

    responsibility model

    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
     उल्लेख
    0.51
     मातर
    0.51
    志森
    0.50
    к
    0.50
     Raja
    0.49
    चाप
    0.49
    ij
    0.48
     Olimpi
    0.47
    ermodel
    0.47
    forma
    0.46
    POSITIVE LOGITS
    ”
    0.46
     expropri
    0.41
     রি
    0.41
    释
    0.41
     heartfelt
    0.40
    야
    0.40
    Substituting
    0.40
    AUX
    0.40
    داد
    0.40
    슝
    0.39
    Activations Density 0.000%

    No Known Activations