© 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. 133186
    Prev
    Next
    INDEX
    Explanations

    invest and card applications

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

    designed for and limitations

    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
    >>>
    0.65
     Bury
    0.58
    =>{
    0.54
    \-
    0.52
    }>
    0.51
    '>
    0.49
     PIPE
    0.47
    ►
    0.46
    :>
    0.46
     i
    0.46
    POSITIVE LOGITS
    aide
    0.47
    ুনা
    0.46
    াচিত
    0.46
     striis
    0.46
     টালি
    0.45
    ीड
    0.45
    UTURE
    0.45
    ранд
    0.44
     colabor
    0.44
    勋
    0.43
    Activations Density 0.000%

    No Known Activations