© 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. 250903
    Prev
    Next
    INDEX
    Explanations

    telephone numbers, contact information

    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
    стта
    0.48
     નવી
    0.47
     اض
    0.47
    ोसी
    0.46
     nuove
    0.44
    νει
    0.44
    荧
    0.44
    новый
    0.44
    枧
    0.43
    חד
    0.43
    POSITIVE LOGITS
    寶
    0.45
    貴
    0.44
    ।’’
    0.41
     işte
    0.41
    Barnes
    0.40
    Kenny
    0.39
     opérateur
    0.39
     bj
    0.39
     é
    0.39
     korist
    0.39
    Activations Density 0.001%

    No Known Activations