© 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. 69920
    Prev
    Next
    INDEX
    Explanations

    leaning on or over

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

    leaning forward

    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
    f
    0.59
    d
    0.56
    ワンピース
    0.50
    İ
    0.46
    v
    0.46
    j
    0.46
    ディズニー
    0.46
     veloce
    0.45
    o
    0.44
    lo
    0.44
    POSITIVE LOGITS
    傾
    0.61
     leaning
    0.54
    倾
    0.52
    仳
    0.52
     tilted
    0.51
     leans
    0.50
     기울
    0.49
    ;
    0.49
     скло
    0.48
     slant
    0.46
    Activations Density 0.024%

    No Known Activations