© 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. 38695
    Prev
    Next
    INDEX
    Explanations

    magazine and serial subscriptions

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

    magazines and subscriptions

    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
    ɽ
    0.49
     ডেভেল
    0.47
    >{</
    0.46
     trembled
    0.45
     rigidbody
    0.45
     morphisms
    0.45
     deformation
    0.43
     waypoint
    0.43
    <()>
    0.43
    ɺ
    0.43
    POSITIVE LOGITS
     ISSN
    1.09
     Magazines
    1.01
     magazine
    0.99
     Subscription
    0.94
     subscription
    0.94
     Magazine
    0.94
     subscriptions
    0.93
    ISSN
    0.93
     magazines
    0.92
     subscribing
    0.86
    Activations Density 0.078%

    No Known Activations