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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111229
    Prev
    Next
    INDEX
    Explanations

    congratulations or college acceptance

    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_10/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
     but
    -1.88
     (
    -1.40
    </em>
    -1.38
     destined
    -1.30
     Hinblick
    -1.20
     According
    -1.16
     späteren
    -1.15
     invitamos
    -1.11
    Appellants
    -1.08
    ACTERS
    -1.07
    POSITIVE LOGITS
    they
    1.47
     about
    1.45
     aggiungere
    1.41
    ldots
    1.41
    锃
    1.39
     ボア
    1.36
    pendentif
    1.35
     gyvento
    1.34
     almeno
    1.33
     konfig
    1.33
    Activations Density 0.035%

    No Known Activations