© 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. 182360
    Prev
    Next
    INDEX
    Explanations

    three dimensional

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

    capturing attention or ending narratives

    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
     Abstand
    0.52
    )));
    0.45
    rific
    0.44
     לש
    0.43
     Sprache
    0.42
     خطاب
    0.42
    )).
    0.41
    
    0.41
    estellten
    0.41
     Wirtschaft
    0.40
    POSITIVE LOGITS
    in
    0.49
     hydraul
    0.49
    م
    0.49
     theaters
    0.47
    sister
    0.46
    M
    0.46
    冗
    0.45
     franch
    0.45
    放送
    0.44
     kamera
    0.44
    Activations Density 0.002%

    No Known Activations