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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49622
    Prev
    Next
    INDEX
    Explanations

    phone calls and skip hire

    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
     librarian
    -0.80
    iglie
    -0.76
    tilizer
    -0.73
     differential
    -0.72
    ވ
    -0.70
    alibaba
    -0.69
     Veranstaltung
    -0.69
     email
    -0.69
    martre
    -0.68
    Stam
    -0.68
    POSITIVE LOGITS
     Phone
    1.46
     Telephone
    1.31
    Phone
    1.31
     phone
    1.25
    Telephone
    1.22
     Dial
    1.16
     VoIP
    1.15
    Dial
    1.13
    电话
    1.13
    Caller
    1.13
    Activations Density 0.015%

    No Known Activations