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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 51
    Prev
    Next
    INDEX
    Explanations

    words starting with inv

    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
     förslag
    -0.82
     execu
    -0.78
     snare
    -0.76
    minos
    -0.74
    راء
    -0.73
    VERS
    -0.72
     Baumwolle
    -0.72
     Perseverance
    -0.71
     entier
    -0.71
    forming
    -0.71
    POSITIVE LOGITS
     inv
    1.56
     INV
    1.51
    inv
    1.44
     Inv
    1.40
    Inv
    1.20
    INV
    1.17
    TargetException
    0.93
     invincible
    0.84
     nikdy
    0.84
    invit
    0.77
    Activations Density 0.030%

    No Known Activations