© 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. 51012
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    phone numbers and contact details

    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
     ಕಾನೂ
    0.47
    郵便
    0.46
    marital
    0.46
    𝚆
    0.46
     ಕುಟ
    0.45
     ناخد
    0.44
     ناخذ
    0.44
    ल्पन
    0.44
    dmn
    0.44
    ൧
    0.44
    POSITIVE LOGITS
     and
    0.59
    ä
    0.54
    ,
    0.53
     of
    0.51
     that
    0.50
     about
    0.49
     used
    0.49
     down
    0.48
     was
    0.47
     up
    0.46
    Activations Density 0.001%

    No Known Activations