© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75107
    Prev
    Next
    INDEX
    Explanations

    if/then consequences

    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
    荭
    -1.26
    ранда
    -1.14
     También
    -1.13
     Ook
    -1.13
    También
    -1.13
    geschwindigkeit
    -1.12
     devraient
    -1.10
     siè
    -1.10
    assioned
    -1.09
    ISER
    -1.08
    POSITIVE LOGITS
     any
    1.60
     required
    1.50
     require
    1.31
     found
    1.25
     requested
    1.24
     change
    1.21
     necessary
    1.16
     additional
    1.14
     необходимо
    1.10
     need
    1.09
    Activations Density 0.025%

    No Known Activations