© 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. 177680
    Prev
    Next
    INDEX
    Explanations

    able to

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

    How does persona

    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
     ámbitos
    0.54
     केसा
    0.50
    personen
    0.49
     бел
    0.48
     ==>
    0.46
     convince
    0.45
    ción
    0.45
     alguém
    0.45
     бренда
    0.45
    स्पून
    0.45
    POSITIVE LOGITS
    ג
    0.47
    霊
    0.44
     Gag
    0.43
    浴
    0.42
    ophy
    0.40
    τ
    0.40
    গ
    0.39
    泰
    0.39
    権
    0.39
    晏
    0.39
    Activations Density 0.000%

    No Known Activations