© 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. 202560
    Prev
    Next
    INDEX
    Explanations

    contact you regarding orders

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

    iron production and compute networks

    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
     njeg
    0.49
    ó
    0.46
    plings
    0.44
     vollständ
    0.44
    u
    0.43
    án
    0.42
    rosion
    0.42
     jego
    0.42
     całej
    0.42
     فونی
    0.41
    POSITIVE LOGITS
    קו
    0.50
    Inverse
    0.48
    TXT
    0.48
    PUT
    0.46
     যেটা
    0.46
    Downward
    0.45
    蝟
    0.45
    Liu
    0.45
    OVER
    0.45
    WHITE
    0.45
    Activations Density 0.001%

    No Known Activations