© 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. 5170
    Prev
    Next
    INDEX
    Explanations

    creating or performing actions

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

    calculate quantities

    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
     Kön
    0.46
    hened
    0.45
     அங்க
    0.43
     Hadd
    0.42
    き
    0.40
     одну
    0.39
     Bás
    0.38
    ests
    0.38
     Esper
    0.38
    recogn
    0.38
    POSITIVE LOGITS
    ፑ
    0.46
    。」
    0.45
     пенсии
    0.44
    評價
    0.44
    ServiceGroupID
    0.44
    বা
    0.42
     hobbies
    0.42
     tejidos
    0.41
    isVideoRecording
    0.41
    ческа
    0.41
    Activations Density 0.000%

    No Known Activations