© 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. 241995
    Prev
    Next
    INDEX
    Explanations

    measures aimed at or requests from

    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
    방송
    0.50
    前
    0.48
    日前
    0.47
    脆
    0.46
    𝚋
    0.46
     bombed
    0.45
    𝚊
    0.45
    く
    0.45
    বাড়
    0.44
     strung
    0.44
    POSITIVE LOGITS
     সময়ই
    0.47
     เศ
    0.45
     പിറ
    0.44
     ইলে
    0.44
    ກະ
    0.43
     ഓർ
    0.42
     देखील
    0.42
     कैंडिडेट
    0.42
    <unused88>
    0.41
     खुलकर
    0.41
    Activations Density 0.001%

    No Known Activations