© 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. 22-GEMMASCOPE-RES-131K
    7. 71
    Prev
    Next
    INDEX
    Explanations

    This invention relates to

    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_22/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
    vereignty
    -1.23
    وزن
    -1.10
     和
    -1.09
    𖣔
    -1.07
    秾
    -1.06
     loob
    -1.05
     TECHNIQUE
    -1.05
     årene
    -1.05
    𒊹
    -1.03
     EQUIPMENT
    -1.02
    POSITIVE LOGITS
    цезда
    1.22
     nasz
    1.06
     inmediatamente
    1.06
     plausible
    1.05
     wzgl
    1.04
    学び
    1.04
    ,
    1.02
    彼らの
    1.01
     dieses
    1.01
     they
    0.99
    Activations Density 0.000%

    No Known Activations