© 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. 181807
    Prev
    Next
    INDEX
    Explanations

    inspiration in, requires all, payable, AL, of year, heart to, within 3, then corruption

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

    specific identifying information

    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
     Brother
    0.43
    ۳
    0.40
     chairman
    0.40
     enzyme
    0.40
     அளித்த
    0.39
    ijima
    0.39
     دو
    0.38
     incriminating
    0.38
     Incorporated
    0.38
     któ
    0.38
    POSITIVE LOGITS
    u
    0.59
    premi
    0.53
    Svg
    0.51
    krieg
    0.49
     taxe
    0.48
    hd
    0.48
    hear
    0.48
    uhe
    0.47
    ileg
    0.46
    hbar
    0.46
    Activations Density 0.000%

    No Known Activations