© 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. 98776
    Prev
    Next
    INDEX
    Explanations

    the [entity name]

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

    sports and competition terms

    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
    買う
    0.46
    IPAL
    0.44
    Carrito
    0.44
     حوالے
    0.44
    MJX
    0.42
    ﭜ
    0.42
     ಬಳಕೆ
    0.41
    ፉ
    0.40
    WN
    0.40
    依法
    0.39
    POSITIVE LOGITS
     confidence
    0.51
     Canadians
    0.49
     Asians
    0.48
     young
    0.45
     ball
    0.45
     h
    0.44
     Flames
    0.44
     partition
    0.44
     expectation
    0.44
     zwischen
    0.44
    Activations Density 0.079%

    No Known Activations