© 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. 12833
    Prev
    Next
    INDEX
    Explanations

    (c) or this paper

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

    this paper, analogy, blog, study

    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
     divides
    0.41
    afar
    0.40
    
    0.38
    oryt
    0.38
     SUPPLEMENT
    0.37
    cony
    0.36
    kę
    0.36
     mistakes
    0.36
    lady
    0.36
     secretions
    0.35
    POSITIVE LOGITS
    aternion
    0.45
     skoro
    0.44
    SizeMode
    0.42
     ಎರಡು
    0.41
    ToArabic
    0.41
    ขอ
    0.40
     solicita
    0.40
    $-$,
    0.40
    iotsitewise
    0.39
    ווע
    0.39
    Activations Density 0.000%

    No Known Activations