© 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. 61834
    Prev
    Next
    INDEX
    Explanations

    devices

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

    non-english texts

    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
    ael
    0.49
    ke
    0.48
     Magdal
    0.48
    ko
    0.44
    <strong>
    0.43
    kir
    0.43
    contro
    0.42
     circonstances
    0.42
    ৎ
    0.42
                                   
    0.41
    POSITIVE LOGITS
     火
    0.46
     画
    0.46
     액
    0.46
     зака
    0.44
    いが
    0.44
     പിന്നീട്
    0.44
    តម្លៃ
    0.42
    мата
    0.42
    價
    0.42
    蚂
    0.41
    Activations Density 0.000%

    No Known Activations