© 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. 34-GEMMASCOPE-RES-131K
    4. 45346
    Prev
    Next
    INDEX
    Explanations

    there is a

    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
     wszystkie
    -1.37
    ternos
    -1.31
    ᄋ
    -1.25
    lında
    -1.18
    kedés
    -1.17
    kozó
    -1.16
    corbic
    -1.16
    ualaikum
    -1.15
     posled
    -1.15
     纹
    -1.15
    POSITIVE LOGITS
     a
    3.22
     no
    2.69
     an
    2.16
     some
    1.91
     plenty
    1.78
     nothing
    1.42
     room
    1.40
     lots
    1.40
     something
    1.38
     two
    1.36
    Activations Density 0.078%

    No Known Activations