© 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. 7058
    Prev
    Next
    INDEX
    Explanations

    type returned

    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
    Rh
    0.50
    ada
    0.49
    Las
    0.48
    Sy
    0.47
    i
    0.45
     hemisphere
    0.44
    Ay
    0.43
    Ada
    0.43
    Но
    0.43
     employs
    0.43
    POSITIVE LOGITS
    \<
    0.55
     എന്നാല്‍
    0.54
    \<^
    0.52
    <(
    0.51
     ため
    0.51
     みたい
    0.50
    䟧
    0.50
     dxe
    0.49
     Administrat
    0.49
     überprüfen
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.