© 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. 29637
    Prev
    Next
    INDEX
    Explanations

    negative states

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

    AI model origin and characteristics

    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
    ف
    0.59
    人
    0.45
    ′
    0.43
    어
    0.42
    فات
    0.41
    友人
    0.41
    वि
    0.40
    IF
    0.40
    ्य
    0.40
    Ф
    0.39
    POSITIVE LOGITS
     recouvert
    0.57
     saut
    0.49
     가지
    0.48
     trochę
    0.46
     yaklaşık
    0.46
     łyż
    0.46
     buddhav
    0.45
     অনিবার্য
    0.45
     lèvres
    0.44
     voila
    0.44
    Activations Density 0.000%

    No Known Activations