© 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. 209428
    Prev
    Next
    INDEX
    Explanations

    because, required, needed

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

    likely original or fact-based

    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
    ｺ
    0.41
    굉
    0.38
    яви
    0.36
     homomorphism
    0.35
     homomorphisms
    0.35
    <0xEC>
    0.35
    审
    0.34
    Homme
    0.34
    ิ
    0.34
    ז
    0.34
    POSITIVE LOGITS
     eventuali
    0.40
     Çünkü
    0.39
     因
    0.38
    ിക്കേണ്ട
    0.37
    其他
    0.36
    ക്കേണ്ട
    0.36
    所需的
    0.34
     hatten
    0.34
    原本
    0.34
     因為
    0.34
    Activations Density 0.001%

    No Known Activations