© 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. 24702
    Prev
    Next
    INDEX
    Explanations

    above or upward direction

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

    caret symbol or up arrow

    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
    ри
    0.49
    عين
    0.44
    $\
    0.43
     Entscheidung
    0.41
    iminaries
    0.40
     compensatory
    0.40
    菲
    0.40
    PlainText
    0.39
    인을
    0.39
    imizi
    0.38
    POSITIVE LOGITS
     above
    0.61
     ABOVE
    0.61
     ↓
    0.59
     powy
    0.57
     acima
    0.55
     ऊपर
    0.52
     Above
    0.51
     ↑
    0.50
     takže
    0.50
    ↑
    0.50
    Activations Density 0.002%

    No Known Activations