© 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. 219482
    Prev
    Next
    INDEX
    Explanations

    German, Spanish, Russian, Hindi, Tamil words

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

    trigger warnings and disclaimers

    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
    电阻
    0.47
    ור
    0.43
    חי
    0.43
    يلي
    0.42
    웹
    0.42
     Unterschied
    0.42
    asp
    0.42
    BSD
    0.41
    info
    0.41
    كري
    0.40
    POSITIVE LOGITS
     Gemä
    0.58
     julho
    0.57
     în
    0.51
    𝚁
    0.50
     प्रकर
    0.49
     являются
    0.49
    ных
    0.48
     формирования
    0.48
     यंदा
    0.47
     தங்கள்
    0.46
    Activations Density 0.001%

    No Known Activations