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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 743
    Prev
    Next
    INDEX
    Explanations

    company said/announced

    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_10/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
    ListModel
    -1.45
     où
    -1.41
    NOWLEDGE
    -1.40
    balah
    -1.40
     anderen
    -1.35
     wiele
    -1.33
    玙
    -1.33
    jorie
    -1.27
     innych
    -1.23
    urlopen
    -1.23
    POSITIVE LOGITS
     аса
    1.41
     —
    1.30
    ~”
    1.30
     kuitenkin
    1.27
     avevano
    1.24
    喼
    1.23
    💞
    1.19
    냅
    1.18
     nôtre
    1.17
    ))$_
    1.16
    Activations Density 0.036%

    No Known Activations