© 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. 204746
    Prev
    Next
    INDEX
    Explanations

    without your

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

    If, without, 5, CTRL

    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
     bổ
    0.45
     Nantucket
    0.43
     dje
    0.42
     ISI
    0.42
    嬬
    0.42
     bambino
    0.42
     Fu
    0.42
     hè
    0.42
    ং
    0.42
     gio
    0.42
    POSITIVE LOGITS
    renner
    0.56
    la
    0.52
    ors
    0.49
    datas
    0.49
    ja
    0.49
    ert
    0.48
    ke
    0.48
    {'
    0.48
    nl
    0.47
    wil
    0.47
    Activations Density 0.000%

    No Known Activations