© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65642
    Prev
    Next
    INDEX
    Explanations

    plans and policies

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

    attracting customers or users

    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
    ຶ່ງ
    0.46
    າມາດ
    0.45
    tsioon
    0.45
     पुनर्
    0.44
    CameraOpened
    0.44
     Моск
    0.44
     konstru
    0.44
    <unused1112>
    0.43
     Owls
    0.43
     stench
    0.43
    POSITIVE LOGITS
    plans
    0.55
    printed
    0.51
    issuer
    0.50
    plan
    0.49
    i
    0.49
    ו
    0.47
    ix
    0.47
    at
    0.47
    г
    0.46
    ive
    0.45
    Activations Density 0.001%

    No Known Activations