© 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. 122747
    Prev
    Next
    INDEX
    Explanations

    above, Father, lot, opportunities, fathers, category, for

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

    why the curve intersect

    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
    א
    0.65
    Ե
    0.60
    ی
    0.59
    Ս
    0.52
    ஹ
    0.51
     เศ
    0.50
    Фи
    0.50
    י
    0.50
    stilling
    0.49
    Λ
    0.49
    POSITIVE LOGITS
     Sandoval
    0.46
     bandwagon
    0.45
     caravan
    0.45
     situational
    0.44
     boardwalk
    0.43
     Wilcox
    0.42
     lefty
    0.41
     lucky
    0.41
     Gain
    0.40
     Alton
    0.40
    Activations Density 0.002%

    No Known Activations