© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66146
    Prev
    Next
    INDEX
    Explanations

    deferring recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )–
    -0.84
    Kanpo
    -0.81
     подходит
    -0.80
     biographer
    -0.78
    ?):
    -0.77
     tentativa
    -0.77
    $~
    -0.75
     Quercus
    -0.73
    𝜕
    -0.73
    Ꮐ
    -0.72
    POSITIVE LOGITS
     recovery
    1.38
     recover
    1.30
     Recovery
    1.20
     recovers
    1.20
     Recover
    1.17
     recovered
    1.16
     recovering
    1.13
    recover
    1.06
    Recovery
    1.06
    Recover
    1.00
    Activations Density 0.033%

    No Known Activations