Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8615
    Prev
    Next
    INDEX
    Explanations

    every time

    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
     quello
    -1.17
    ⛦
    -1.13
    seguir
    -1.12
    のですか
    -1.07
     内衣
    -1.06
     allmäh
    -1.02
    ţii
    -1.02
    shaped
    -1.00
     SETS
    -0.99
    nologi
    -0.98
    POSITIVE LOGITS
     we
    2.66
     they
    2.28
     you
    2.28
     someone
    2.16
     anyone
    1.77
     that
    1.53
     somebody
    1.45
     there
    1.44
     any
    1.40
     something
    1.38
    Activations Density 0.018%

    No Known Activations