© 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. 161325
    Prev
    Next
    INDEX
    Explanations

    obsession is, image on, along with, speak to, picture on, chase set, could experience

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

    homomorphisms preserve order, frameworks, file paths

    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
     अहमदाबाद
    0.53
    और
    0.51
    買
    0.51
    䡆
    0.49
     अपडेट
    0.49
     சுமார்
    0.49
     mewah
    0.49
     न्यूयॉर्क
    0.48
     मुंबई
    0.47
     ダーク
    0.47
    POSITIVE LOGITS
    Wrap
    0.44
    ^{\
    0.43
    Scalar
    0.43
    Rx
    0.43
    лів
    0.42
    KeyPressed
    0.42
    Vertical
    0.42
    Paths
    0.42
    Time
    0.41
    টির
    0.41
    Activations Density 0.001%

    No Known Activations