© 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. 245048
    Prev
    Next
    INDEX
    Explanations

    end of phrase

    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
     зоны
    0.52
     ਮੰ
    0.48
    诸多
    0.47
    Parrocchia
    0.46
    า
    0.46
     헤
    0.46
     পার্থ
    0.44
    सम्म
    0.44
    interpolate
    0.44
    eryka
    0.44
    POSITIVE LOGITS
    biti
    0.48
     Arms
    0.44
    できた
    0.44
     One
    0.43
     offensively
    0.43
     &$
    0.43
    reib
    0.43
    حي
    0.42
     Duv
    0.42
    ivr
    0.42
    Activations Density 0.000%

    No Known Activations