© 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. 251161
    Prev
    Next
    INDEX
    Explanations

    valid with

    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
    マル
    0.55
    想
    0.52
    ла
    0.50
    u
    0.50
    lan
    0.49
    Έ
    0.49
    los
    0.48
    л
    0.47
    Тре
    0.47
    不能
    0.47
    POSITIVE LOGITS
     tess
    0.59
     кот
    0.51
     liturg
    0.49
     만들어
    0.48
     기간
    0.48
     darkening
    0.48
     kite
    0.47
     labyrinth
    0.46
     tessel
    0.46
     ê
    0.46
    Activations Density 0.000%

    No Known Activations