© 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. 88915
    Prev
    Next
    INDEX
    Explanations

    evaluated, marginal, pert, best

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

    doorbell rang, remember that, room layout, local administrator, lifespan and

    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
    𝔰
    0.50
    وی
    0.49
    י
    0.48
    לא
    0.45
     ソ
    0.45
    λα
    0.44
    ,'
    0.44
     Mania
    0.43
     mon
    0.43
     الص
    0.43
    POSITIVE LOGITS
    父亲
    0.57
    擞
    0.54
    teren
    0.51
    rogram
    0.50
    arz
    0.50
    સભા
    0.49
    ährend
    0.49
    érrez
    0.49
     えっと
    0.49
    zeti
    0.49
    Activations Density 0.001%

    No Known Activations