© 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. 231953
    Prev
    Next
    INDEX
    Explanations

    documentation and movement

    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
    :
    0.55
    )$
    0.47
     Middle
    0.47
     IN
    0.47
     Dish
    0.46
     bond
    0.46
     INR
    0.45
     US
    0.45
    !)
    0.45
     CO
    0.45
    POSITIVE LOGITS
    𒅴
    0.54
    導演
    0.49
    暌
    0.48
    𒊏
    0.47
    ర్స్
    0.47
     เลย
    0.46
    以來
    0.46
    睽
    0.46
    谥
    0.46
    Mâc
    0.46
    Activations Density 0.001%

    No Known Activations