© 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. 70430
    Prev
    Next
    INDEX
    Explanations

    tune, password, taxes, footsteps, join, showed, activate

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

    structured lists and categorizations

    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
    ቖ
    0.52
     同时
    0.50
    ură
    0.50
    。”
    0.50
    同时
    0.45
    IndexArray
    0.45
    ⓤ
    0.45
    ρική
    0.44
    ície
    0.43
    брав
    0.43
    POSITIVE LOGITS
     eigener
    0.51
     recentes
    0.47
     deri
    0.47
     abgerufen
    0.47
     ZZ
    0.46
     Beer
    0.45
     DZ
    0.44
    ০০
    0.44
    0
    0.43
     Mö
    0.43
    Activations Density 0.002%

    No Known Activations