© 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. 227877
    Prev
    Next
    INDEX
    Explanations

    rapid strides, arm action

    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
     coloured
    0.43
    in
    0.43
    EQU
    0.43
    釆
    0.43
    🔅
    0.42
    Coat
    0.42
     cùng
    0.41
     về
    0.41
     המ
    0.40
    由
    0.40
    POSITIVE LOGITS
     वॉलेट
    0.47
     Олимпий
    0.45
     artériel
    0.45
     आंसर
    0.44
     அவர்களுக்கு
    0.43
     étendue
    0.43
    ्यूस
    0.43
     trenger
    0.43
     म्हणजेच
    0.42
     bisogno
    0.41
    Activations Density 0.001%

    No Known Activations