© 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. 160425
    Prev
    Next
    INDEX
    Explanations

    four sectionsoriented photosoften try

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

    exploring context and reasons why

    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
    無料で
    0.42
     聞い
    0.42
    負担
    0.41
    ಮಂತ್ರಿ
    0.40
     прошу
    0.40
    ("\"
    0.39
     점점
    0.39
    擾
    0.38
     मुफ्त
    0.38
     ограни
    0.38
    POSITIVE LOGITS
     Ancient
    0.48
     belleza
    0.48
     మన
    0.48
     సాహిత
    0.46
     tentunya
    0.46
     এই
    0.46
     meskipun
    0.45
     Although
    0.44
     khususnya
    0.44
     although
    0.43
    Activations Density 0.000%

    No Known Activations