© 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. 139175
    Prev
    Next
    INDEX
    Explanations

    establish a basis

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

    establish baseline

    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
    3
    0.85
    4
    0.82
    يل
    0.80
    6
    0.78
    5
    0.69
     dreamed
    0.68
    <unused2162>
    0.68
    of
    0.66
    \
    0.64
    1
    0.63
    POSITIVE LOGITS
    established
    1.02
    establish
    0.97
    establishing
    0.95
     established
    0.90
     Establish
    0.90
     establish
    0.86
    Establishing
    0.84
     estabele
    0.83
     establishing
    0.83
    確立
    0.82
    Activations Density 0.088%

    No Known Activations