© 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. 32033
    Prev
    Next
    INDEX
    Explanations

    completing phrases or words

    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
    ”—
    -1.55
    kissen
    -1.47
    ⸗
    -1.41
    `]
    -1.40
    —¿
    -1.40
     Verständ
    -1.39
    を行いました
    -1.38
     conocida
    -1.36
    ׃
    -1.35
    ⿻
    -1.34
    POSITIVE LOGITS
     –
    1.52
     dolorosa
    1.35
     Grüßen
    1.33
    を
    1.30
     teint
    1.30
     pijama
    1.27
     Când
    1.27
    ਫ਼
    1.26
    ～！
    1.26
     peluche
    1.26
    Activations Density 0.467%

    No Known Activations