© 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. 192100
    Prev
    Next
    INDEX
    Explanations

    hand carved stamp

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

    arc, GPT, table, party, sounds

    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
    K
    0.52
     tekn
    0.51
     technician
    0.51
     Trebuie
    0.51
     Pens
    0.50
     Technician
    0.50
     Tekn
    0.49
     Ph
    0.48
     Query
    0.48
    დან
    0.48
    POSITIVE LOGITS
    ंगिक
    0.50
    ん
    0.46
    いわ
    0.45
    ANNEL
    0.44
    ਾ
    0.43
     pathologies
    0.43
    anova
    0.41
    軽い
    0.41
    layered
    0.41
    ರಳ
    0.41
    Activations Density 0.000%

    No Known Activations