© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 148281
    Prev
    Next
    INDEX
    Explanations

    especially regarding long-term

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

    easily

    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
    BOUNDARY
    0.50
    šla
    0.46
    ಸ್ಕೊ
    0.45
     đau
    0.45
    ᱘
    0.44
    θηκαν
    0.44
     attaqu
    0.44
    碼
    0.44
    čil
    0.43
    сында
    0.43
    POSITIVE LOGITS
    /
    0.50
     teie
    0.45
    <h2>
    0.44
    ént
    0.44
    opent
    0.44
     இயக்க
    0.43
    ,
    0.43
    more
    0.42
     Herbst
    0.42
     als
    0.41
    Activations Density 0.001%

    No Known Activations