© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency

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

    city before

    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
    ter
    0.61
     there
    0.59
    ться
    0.54
    rice
    0.52
    simple
    0.52
    ”
    0.51
     offered
    0.51
     Fire
    0.51
     Instead
    0.50
    can
    0.50
    POSITIVE LOGITS
     reduziert
    0.50
    脏
    0.49
    焗
    0.48
    靚
    0.48
     دقیقه
    0.48
     allgeme
    0.47
     Stunde
    0.47
    潴
    0.47
    霭
    0.47
     بیماری
    0.47
    Activations Density 0.000%

    No Known Activations