© 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. 116947
    Prev
    Next
    INDEX
    Explanations

    gift card

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

    compared to

    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
     positiva
    0.52
     positivas
    0.51
    ರಿಸಿ
    0.50
    Positive
    0.50
    POSITIVE
    0.45
    ऊदी
    0.45
     positivos
    0.44
    冏
    0.44
    represents
    0.44
     positiv
    0.44
    POSITIVE LOGITS
     frm
    0.51
     ఇ
    0.46
     đ
    0.45
    homepage
    0.44
     in
    0.43
    frm
    0.43
     цены
    0.42
     crept
    0.42
     !)
    0.42
    ৯
    0.41
    Activations Density 0.002%

    No Known Activations