© 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. 162356
    Prev
    Next
    INDEX
    Explanations

    tagged followed by proteins, changing, Barbados, this, Call

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

    accidentally wander

    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
    ï
    0.48
     selected
    0.47
    TO
    0.46
     TO
    0.45
    selected
    0.45
     adjustable
    0.43
    žel
    0.42
     prominent
    0.42
     spherical
    0.41
     ï
    0.41
    POSITIVE LOGITS
     체험
    0.46
     ори
    0.45
     déprimées
    0.44
    после
    0.42
    醃
    0.42
     inmediatamente
    0.41
     odmah
    0.41
     MAKEINTRESOURCE
    0.41
    дал
    0.41
    ấu
    0.40
    Activations Density 0.000%

    No Known Activations