© 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. 227999
    Prev
    Next
    INDEX
    Explanations

    name, may, wish

    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
     नाइट्र
    0.52
    überkü
    0.52
    afety
    0.51
     பிரச்சின
    0.51
     나머
    0.49
     μεγ
    0.48
     협
    0.48
    ]^{+}$
    0.48
     ખ્ર
    0.48
     नाइट्रेट
    0.48
    POSITIVE LOGITS
     Frequently
    0.46
     by
    0.45
    sty
    0.45
    o
    0.45
     cette
    0.42
     hombre
    0.42
     to
    0.42
     makes
    0.42
    O
    0.41
     Creek
    0.41
    Activations Density 0.000%

    No Known Activations