© 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. 77217
    Prev
    Next
    INDEX
    Explanations

    book titles and domains

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

    identity verification and greetings

    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
    कों
    0.53
    ักษณะ
    0.46
    katapos
    0.45
    myButtons
    0.45
     BusABC
    0.44
    msgSender
    0.44
    𝐁
    0.44
    пис
    0.44
    હ
    0.44
     objectifs
    0.44
    POSITIVE LOGITS
    hing
    0.46
    stitial
    0.43
    nof
    0.42
     طب
    0.41
    viel
    0.40
    ounge
    0.40
    也非常
    0.39
    nings
    0.38
    cap
    0.38
     ని
    0.38
    Activations Density 0.040%

    No Known Activations