© 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. 90456
    Prev
    Next
    INDEX
    Explanations

    greatest possible, largest total

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

    instructions in multiple languages

    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
     anciens
    0.44
    닳
    0.44
     heifers
    0.43
     alleviation
    0.43
     Maa
    0.43
     heinous
    0.43
     cubes
    0.43
     childcare
    0.43
     funded
    0.42
     administration
    0.41
    POSITIVE LOGITS
     Фер
    0.52
    Siempre
    0.47
     Го
    0.47
     थर्म
    0.47
    ir
    0.47
     எப்போதும்
    0.46
    아
    0.46
    Docker
    0.46
     മറ്റ
    0.45
     LocalDateTime
    0.45
    Activations Density 0.000%

    No Known Activations