© 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. 8168
    Prev
    Next
    INDEX
    Explanations

    free items and services

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

    free or at no cost

    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
     कार्याल
    0.46
    远的
    0.44
     খুব
    0.43
     iterates
    0.43
     zoomed
    0.42
     ########.
    0.42
     दूर
    0.41
     iterating
    0.41
     количе
    0.41
     сожа
    0.41
    POSITIVE LOGITS
    免费
    1.49
    免費
    1.46
     free
    1.41
     gratis
    1.38
     бесплат
    1.36
     무료
    1.35
    🆓
    1.32
    free
    1.30
     ücretsiz
    1.30
     FREE
    1.28
    Activations Density 0.231%

    No Known Activations