© 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. 204493
    Prev
    Next
    INDEX
    Explanations

    mine twice

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

    Administration, reservation, pain, eat

    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
    বাগ
    0.52
    茣
    0.50
    뻑
    0.49
    lbrakk
    0.49
    ফটেন্যান্ট
    0.48
    奬
    0.48
    소를
    0.48
     réessayer
    0.46
    𝗟
    0.45
    моль
    0.44
    POSITIVE LOGITS
    en
    0.59
    ens
    0.58
    ali
    0.53
    kin
    0.52
    ik
    0.51
     creating
    0.51
    ou
    0.50
    um
    0.50
     kinet
    0.49
    ong
    0.49
    Activations Density 0.000%

    No Known Activations