© 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. 39208
    Prev
    Next
    INDEX
    Explanations

    reporting stock earnings

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

    machine learning code and 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
    和
    0.47
     ：
    0.46
    ကြီး
    0.45
     和
    0.45
    Labs
    0.43
     विविध
    0.42
    要知道
    0.42
    𝐎
    0.41
    把握
    0.41
     ！
    0.41
    POSITIVE LOGITS
     shaded
    0.43
    pidos
    0.42
    lef
    0.41
     administrators
    0.40
     referenced
    0.40
     específicamente
    0.40
     prothorax
    0.40
    шив
    0.39
     unsurprisingly
    0.39
    चारी
    0.39
    Activations Density 0.018%

    No Known Activations