© 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. 141799
    Prev
    Next
    INDEX
    Explanations

    coloured wall

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

    pronunciation guide for non-native English speakers

    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
     कराई
    0.55
     道
    0.53
    之中
    0.47
    Resposta
    0.47
     कराए
    0.47
     えっ
    0.46
    永
    0.46
    빕
    0.46
     ਸ਼
    0.44
    道
    0.44
    POSITIVE LOGITS
     Medical
    0.49
     Remedies
    0.46
     Victorian
    0.46
     Bi
    0.45
     Phoenix
    0.43
     Medicine
    0.42
    9
    0.42
     Remedy
    0.42
     Edison
    0.42
     Phon
    0.42
    Activations Density 0.000%

    No Known Activations