© 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. 219561
    Prev
    Next
    INDEX
    Explanations

    . or ; then sentence start

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

    focus, stomach, strategy

    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
     പൊതു
    0.47
    ்ச
    0.44
     probabilistic
    0.44
    <unused1653>
    0.43
     Brownian
    0.43
     theoretically
    0.43
    般的
    0.43
    光滑
    0.43
     സി
    0.42
    decomposition
    0.42
    POSITIVE LOGITS
    뺐
    0.47
    ثنين
    0.45
    ①
    0.43
     утром
    0.43
     estratégico
    0.42
    ($
    0.41
    LNG
    0.41
    请
    0.40
    <strong>
    0.40
     !
    0.39
    Activations Density 0.004%

    No Known Activations