© 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. 125744
    Prev
    Next
    INDEX
    Explanations

    join, association, guaranteed, Freedom, shave

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

    potential risks and outcomes

    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
    нь
    0.57
     molécules
    0.56
     الرخصة
    0.49
     लिं
    0.49
     Ví
    0.49
     автомобиль
    0.49
     कोर्ट
    0.48
    窅
    0.48
     мото
    0.48
    倠
    0.48
    POSITIVE LOGITS
    ell
    0.56
    og
    0.50
    comm
    0.49
    segn
    0.48
    seg
    0.48
    ANIEL
    0.47
    presso
    0.46
    ett
    0.46
    ah
    0.45
    vel
    0.43
    Activations Density 0.000%

    No Known Activations