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. 46
    Prev
    Next
    INDEX
    Explanations

    inviting or asking

    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
    توضیحات
    -0.86
    ޭ
    -0.81
    EVALU
    -0.79
    DIRECTOR
    -0.79
    ulescu
    -0.78
    PUBL
    -0.77
    CHAIR
    -0.77
    TypeString
    -0.77
    Évaluation
    -0.77
    ingroup
    -0.77
    POSITIVE LOGITS
     asking
    2.86
     inviting
    2.44
     Asking
    2.27
     invitation
    2.14
    Asking
    2.11
     invite
    2.09
     invites
    2.08
    asking
    1.91
     invitations
    1.80
     invited
    1.77
    Activations Density 0.036%

    No Known Activations