© 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. 57364
    Prev
    Next
    INDEX
    Explanations

    Armada, she, we, award, report

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

    identifying or acknowledging things

    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
    钞
    0.51
     महाराजा
    0.49
     symbol
    0.49
    4
    0.49
    プレミア
    0.46
    博物
    0.46
     symbole
    0.46
    9
    0.44
     Kyr
    0.44
     символ
    0.43
    POSITIVE LOGITS
    plr
    0.49
     السر
    0.47
     diabet
    0.46
     bav
    0.44
    pliance
    0.43
    َيْ
    0.43
    underbrace
    0.42
    adjoint
    0.42
    vedad
    0.41
    haften
    0.41
    Activations Density 0.000%

    No Known Activations