© 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. 1439
    Prev
    Next
    INDEX
    Explanations

    classic or typical examples

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

    classic descriptor

    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
    とても
    0.40
    t
    0.39
     muy
    0.37
     very
    0.36
    ().
    0.36
    ]
    0.35
    ),
    0.34
    ()
    0.34
     veoma
    0.33
    )
    0.33
    POSITIVE LOGITS
     clásica
    0.46
     герой
    0.43
     clásico
    0.41
     classica
    0.40
     klasik
    0.40
     capitalism
    0.38
     underdog
    0.37
     revenge
    0.37
     نوفمبر
    0.37
     класси
    0.37
    Activations Density 0.304%

    No Known Activations