© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1248
    Prev
    Next
    INDEX
    Explanations

    recovery and restoration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     vorg
    1.64
    듄
    1.43
     herum
    1.34
    외
    1.30
    ombie
    1.30
     dve
    1.26
    특
    1.26
     मोठे
    1.24
    |=
    1.23
    눠
    1.22
    POSITIVE LOGITS
     recuperar
    2.07
     regained
    2.04
     retomar
    2.00
     பழைய
    1.88
     recob
    1.88
     regain
    1.84
     Recover
    1.82
     indietro
    1.82
     复
    1.81
     restoration
    1.81
    Activations Density 1.323%

    No Known Activations