© 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. 198474
    Prev
    Next
    INDEX
    Explanations

    options or rates

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

    formal and

    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
    appropri
    0.57
    estimators
    0.49
    routers
    0.48
    landmarks
    0.48
    constants
    0.47
    ්ර
    0.46
    阍
    0.46
    Bạn
    0.45
     Nếu
    0.45
    atributos
    0.45
    POSITIVE LOGITS
     molle
    0.53
     ½
    0.50
     Ersatz
    0.48
     kindle
    0.48
     ¼
    0.48
     replace
    0.48
     millennium
    0.46
     dle
    0.45
     demi
    0.45
     pien
    0.44
    Activations Density 0.000%

    No Known Activations