© 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. 141625
    Prev
    Next
    INDEX
    Explanations

    need to

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

    opposite, different, trademark, potential

    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
    سو
    0.57
    qda
    0.54
     siden
    0.46
     دینا
    0.45
     reino
    0.44
    ن
    0.44
    ugel
    0.44
    ørte
    0.44
    н
    0.44
    ugin
    0.43
    POSITIVE LOGITS
    c
    0.59
    Haryana
    0.50
    t
    0.46
    दूर
    0.46
     શરૂ
    0.46
    ேட்
    0.46
    𝓂
    0.46
    January
    0.45
    Europe
    0.45
    September
    0.44
    Activations Density 0.000%

    No Known Activations