© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4122
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

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

    topics and categories

    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_53_width_65k_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
     baffling
    0.38
    <unused2200>
    0.38
     umjet
    0.37
    <unused2130>
    0.37
    <unused251>
    0.36
    <unused472>
    0.36
    <unused465>
    0.35
     mehreren
    0.35
     diverses
    0.35
    <unused312>
    0.34
    POSITIVE LOGITS
    வனின்
    0.45
     ওরফে
    0.38
    만에
    0.37
     AcOEt
    0.37
    ჯგუფი
    0.36
     అనేది
    0.36
    ™
    0.36
     cendré
    0.35
    </td>
    0.35
    来店
    0.35
    Activations Density 0.284%

    No Known Activations