© 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. 203748
    Prev
    Next
    INDEX
    Explanations

    international or non-english words

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

    similar to other brands

    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
     pripad
    0.49
     ne
    0.47
     pole
    0.46
     ide
    0.45
     foli
    0.45
     vid
    0.45
     I
    0.43
     ballon
    0.43
     buton
    0.43
    ម
    0.43
    POSITIVE LOGITS
     artigo
    0.51
    <unused73>
    0.50
     인도
    0.50
     או
    0.49
     הס
    0.48
     አስ
    0.47
     হ্রাস
    0.47
     தவிர்க்க
    0.47
    ುಕ
    0.46
     ဦး
    0.46
    Activations Density 0.000%

    No Known Activations