© 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. 199974
    Prev
    Next
    INDEX
    Explanations

    efficiency, importance, products, food

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

    introduction words

    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
    u
    0.55
    bleeds
    0.54
     фаразлары
    0.53
    หมด
    0.49
    oved
    0.46
    これが
    0.46
    seekers
    0.45
    iu
    0.45
    eker
    0.45
     будущего
    0.44
    POSITIVE LOGITS
     castillo
    0.46
     impulsar
    0.46
     Doherty
    0.46
     hicimos
    0.45
     tarik
    0.45
     (
    0.44
     hice
    0.43
    ％
    0.43
     Regierung
    0.43
     instalar
    0.42
    Activations Density 0.001%

    No Known Activations