© 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. 233202
    Prev
    Next
    INDEX
    Explanations

    English word followed by another English word

    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
    šan
    0.52
    ットフォーム
    0.52
     blindness
    0.50
    ]^{-
    0.46
     ब्लाइंड
    0.45
     हि
    0.45
    大変
    0.45
     environmentally
    0.44
     समाजसेवी
    0.44
    pooled
    0.43
    POSITIVE LOGITS
     ruolo
    0.49
     assegn
    0.49
    氪
    0.49
    知道
    0.49
     operações
    0.47
     impress
    0.47
    unter
    0.47
    雒
    0.47
    دو
    0.46
    ધો
    0.46
    Activations Density 0.000%

    No Known Activations