© 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. 73952
    Prev
    Next
    INDEX
    Explanations

    food catering startup

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

    empathy and support

    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
    b
    0.51
    between
    0.50
    attended
    0.47
    overlaps
    0.47
    Establishing
    0.47
    near
    0.46
    Bl
    0.46
    because
    0.46
    establishing
    0.45
     Czechoslovakia
    0.45
    POSITIVE LOGITS
     blogging
    0.52
     asalamualaikum
    0.52
    เว็บ
    0.51
     Яндекс
    0.49
     wym
    0.48
     앱
    0.48
     유튜브
    0.48
     шампу
    0.47
     หม
    0.47
     ressources
    0.47
    Activations Density 0.000%

    No Known Activations