© 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. 195668
    Prev
    Next
    INDEX
    Explanations

    our, lovely, routing, heard, benefit

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

    introduction to, King Harald, urge surfing encourages

    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
    łek
    0.52
    עה
    0.51
    δια
    0.51
    ங்கம்
    0.51
    Punch
    0.50
    ફે
    0.50
    ługa
    0.50
    f
    0.49
    Liam
    0.49
    記事
    0.47
    POSITIVE LOGITS
     첨
    0.48
     scanty
    0.47
     saffron
    0.41
     tapering
    0.41
     nenhum
    0.40
    UCK
    0.40
     delta
    0.40
     করিয়৷
    0.40
     erkl
    0.39
     전자
    0.39
    Activations Density 0.000%

    No Known Activations