© 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. 87691
    Prev
    Next
    INDEX
    Explanations

    concerning the

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

    roleplay initiations

    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
     τ
    0.50
    ដែរ
    0.49
     前
    0.47
     α
    0.46
     সঙ্গীত
    0.46
    ponent
    0.44
     সঙ্গীতের
    0.44
    ROME
    0.44
     Provisional
    0.43
     leptons
    0.42
    POSITIVE LOGITS
    andos
    0.48
    适当
    0.48
    onucle
    0.46
     ace
    0.45
     deviate
    0.43
    **,
    0.43
    ınızı
    0.43
     diyor
    0.42
     उचित
    0.42
    unsqueeze
    0.42
    Activations Density 0.000%

    No Known Activations