© 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. 187578
    Prev
    Next
    INDEX
    Explanations

    wine and wins

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

    always 30 years away

    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
     différentes
    0.51
    さまざまな
    0.48
     различни
    0.47
     miesz
    0.47
    擾
    0.46
     różne
    0.46
     فرض
    0.46
    形成的
    0.46
     різні
    0.45
     उत्पत्ति
    0.45
    POSITIVE LOGITS
     afro
    0.48
     sopr
    0.45
     sovere
    0.44
     ઠ
    0.43
     ATG
    0.43
    ido
    0.43
     bebida
    0.42
     exclu
    0.42
    琇
    0.42
     Bulk
    0.41
    Activations Density 0.000%

    No Known Activations