© 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. 78976
    Prev
    Next
    INDEX
    Explanations

    your quality features

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

    especially in complex reasoning

    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
    ſt
    0.45
    וו
    0.44
    ntl
    0.44
     legis
    0.43
    hibit
    0.43
    द्योगिकी
    0.42
    lista
    0.42
    列
    0.42
     includ
    0.42
    mania
    0.42
    POSITIVE LOGITS
     করিয়ে
    0.47
     робо
    0.47
    させていただ
    0.46
    اویر
    0.46
    ক
    0.46
     municipalité
    0.46
     દ્વા
    0.44
     ceny
    0.44
     Akin
    0.43
    BtnFill
    0.42
    Activations Density 0.000%

    No Known Activations