© 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. 61868
    Prev
    Next
    INDEX
    Explanations

    record low

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

    films like video games

    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
    л
    0.55
     други
    0.51
     но
    0.49
    ULTS
    0.48
     풀어
    0.46
     corrobor
    0.45
    .,
    0.44
     свя
    0.44
    ..,
    0.44
    ;,
    0.43
    POSITIVE LOGITS
     funktionieren
    0.52
    欧
    0.51
    قيم
    0.47
     jaren
    0.47
    حيان
    0.46
     Numpy
    0.46
     funktioniert
    0.45
    জ্জনক
    0.44
    الج
    0.44
     éves
    0.44
    Activations Density 0.000%

    No Known Activations