© 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. 105767
    Prev
    Next
    INDEX
    Explanations

    chief scene

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

    Now, significant implications

    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
     retrospect
    0.46
    スタンド
    0.42
     demise
    0.42
    エロー
    0.42
    キシ
    0.41
    ImageAlign
    0.41
    Title
    0.41
    そ
    0.41
    pertino
    0.40
    ラジオ
    0.40
    POSITIVE LOGITS
     Eliza
    0.53
     Fish
    0.51
     Then
    0.50
     ganze
    0.50
    t
    0.50
     karde
    0.50
     Honour
    0.49
     Later
    0.49
     gode
    0.49
     Tras
    0.48
    Activations Density 0.001%

    No Known Activations