© 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. 84217
    Prev
    Next
    INDEX
    Explanations

    personal conversation and movies

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

    most phones

    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
    फना
    0.47
    otard
    0.46
     grassroots
    0.44
     みんな
    0.44
    ᱖
    0.44
     работников
    0.43
    দেশিক
    0.42
     semua
    0.42
     termites
    0.42
     appointees
    0.42
    POSITIVE LOGITS
    1
    0.52
     Smartphone
    0.51
     In
    0.50
     From
    0.48
     Aladdin
    0.47
     from
    0.46
     från
    0.45
     Smartphones
    0.45
    ข้อมูล
    0.44
    In
    0.44
    Activations Density 0.003%

    No Known Activations