© 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. 194793
    Prev
    Next
    INDEX
    Explanations

    without limiting

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

    horizontal and vertical spars

    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
    (
    0.58
    ugg
    0.47
    "
    0.46
    jam
    0.46
    pos
    0.46
    Listed
    0.46
    Adder
    0.44
    bay
    0.43
    units
    0.43
    kept
    0.43
    POSITIVE LOGITS
    <unused981>
    0.62
     trase
    0.61
     aquare
    0.59
     diagonalizable
    0.59
     ອ
    0.55
     impon
    0.55
     대로
    0.55
     પરિ
    0.53
     查询
    0.53
     कार्
    0.52
    Activations Density 0.000%

    No Known Activations