© 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. 209446
    Prev
    Next
    INDEX
    Explanations

    an FBI, the right, complete with

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

    hawkish, vulnerable

    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
    verted
    0.49
     marie
    0.49
     seu
    0.46
    gruppen
    0.45
    foundland
    0.45
     سعید
    0.44
     nyt
    0.43
    -
    0.43
     munic
    0.42
    quelle
    0.42
    POSITIVE LOGITS
    োয়ার
    0.45
    YES
    0.45
    টিস
    0.45
    Broadcast
    0.44
    桥
    0.43
    ায়
    0.43
    Have
    0.43
    Okay
    0.42
    Btn
    0.42
    okay
    0.42
    Activations Density 0.000%

    No Known Activations