© 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. 73358
    Prev
    Next
    INDEX
    Explanations

    iPod, iPhone, devices

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

    presentation or completeness

    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
    letto
    0.47
     is
    0.46
     ai
    0.46
     de
    0.46
     la
    0.46
     can
    0.45
     nourish
    0.45
     R
    0.44
     contender
    0.44
     ventures
    0.43
    POSITIVE LOGITS
    𝙀
    0.50
     ناب
    0.50
    诱
    0.49
    rvGroup
    0.49
    基本的に
    0.48
    ❼
    0.48
     সংঘ
    0.47
    motionProxy
    0.46
    ⑸
    0.46
    BeerItem
    0.46
    Activations Density 0.001%

    No Known Activations