© 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. 104953
    Prev
    Next
    INDEX
    Explanations

    public law

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

    International Conflicts & Affairs

    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
     Beograd
    0.50
     Belgrade
    0.46
     case
    0.45
     Huskies
    0.45
    閤
    0.45
     Parkway
    0.45
     PATRIOT
    0.45
     gutted
    0.44
     Romania
    0.44
     Filipino
    0.44
    POSITIVE LOGITS
     განს
    0.54
    isch
    0.51
    ("$
    0.49
     სტ
    0.49
     სპეცი
    0.49
     "$
    0.48
    Specified
    0.48
     ос
    0.47
     rilev
    0.47
     અમને
    0.46
    Activations Density 0.000%

    No Known Activations