© 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. 209162
    Prev
    Next
    INDEX
    Explanations

    getting the message

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

    tracking aspects and connections

    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
     তেমনি
    0.46
    dana
    0.44
    🖊
    0.43
     Técnica
    0.42
    ابی
    0.40
     Pinn
    0.40
    দায়িক
    0.40
    课
    0.40
     Nur
    0.40
    শত
    0.40
    POSITIVE LOGITS
     خانو
    0.51
    طق
    0.47
    .
    0.43
     njeg
    0.43
     horr
    0.42
     infek
    0.42
     f
    0.42
    的人
    0.42
     แก้
    0.41
     ف
    0.41
    Activations Density 0.000%

    No Known Activations