© 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. 157499
    Prev
    Next
    INDEX
    Explanations

    is there a way to

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

    how to add or get

    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
     sports
    0.44
     számos
    0.44
    ":["
    0.43
    ιον
    0.43
     অনেকেই
    0.43
     অনেকে
    0.42
     বেশকিছু
    0.42
     容量
    0.40
    [:
    0.40
    众多
    0.40
    POSITIVE LOGITS
    that
    0.56
     bahwa
    0.50
    believe
    0.49
    ogliamo
    0.47
     lengan
    0.47
    pause
    0.46
    得知
    0.46
    hor
    0.44
    वह
    0.44
     أنه
    0.43
    Activations Density 0.029%

    No Known Activations