© 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. 202741
    Prev
    Next
    INDEX
    Explanations

    photo or lease page method opinion

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

    digital natives or technical 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
    过去
    0.43
    ឃើញ
    0.42
    辣
    0.42
    igheder
    0.41
     एक्ट्रेस
    0.41
    当前
    0.41
    できて
    0.40
    晖
    0.40
    不过
    0.39
    得知
    0.39
    POSITIVE LOGITS
     korte
    0.46
     scienze
    0.45
     notwend
    0.45
     acquist
    0.45
     doit
    0.45
    \|_{\
    0.44
     кеңселер
    0.43
    就可以了
    0.43
     erforder
    0.43
     rozpoc
    0.42
    Activations Density 0.002%

    No Known Activations