© 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. 76926
    Prev
    Next
    INDEX
    Explanations

    writing and independence

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

    control freak?

    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
     返回
    0.50
    -
    0.49
     會
    0.48
     定义
    0.48
    Claim
    0.47
    OnUiThread
    0.46
    NonNull
    0.45
    opoly
    0.45
    ramble
    0.45
    NavController
    0.45
    POSITIVE LOGITS
    𝚋
    0.51
    دی
    0.50
    дик
    0.50
     refract
    0.50
    ຫນ
    0.49
     самостоя
    0.48
     independente
    0.47
     escrit
    0.47
    つけた
    0.47
     escritos
    0.46
    Activations Density 0.000%

    No Known Activations