© 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. 192123
    Prev
    Next
    INDEX
    Explanations

    meeting room or space

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

    actions of my

    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
    »:
    0.50
    ૧
    0.45
     म्हणा
    0.43
     Expl
    0.43
     Aqua
    0.43
     Acquisition
    0.42
     Jump
    0.42
    1
    0.42
    ':
    0.41
     別
    0.41
    POSITIVE LOGITS
    ваемых
    0.44
    contentInset
    0.42
    胍
    0.42
     onların
    0.42
     случаи
    0.42
     respectivas
    0.41
    designated
    0.41
     deras
    0.41
    కునే
    0.41
    rotate
    0.41
    Activations Density 0.000%

    No Known Activations