© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102760
    Prev
    Next
    INDEX
    Explanations

    still followed by a state

    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
    ではでは
    -1.61
    因为他
    -1.58
    さてさて
    -1.55
     whatnot
    -1.45
    それでは
    -1.42
    あなたは
    -1.41
    帮忙
    -1.39
    スポンサーリンク
    -1.38
     if
    -1.34
    or
    -1.33
    POSITIVE LOGITS
    ꪔ
    1.98
     pukul
    1.68
    nehmen
    1.50
     kwiet
    1.49
    洳
    1.47
    ]$}
    1.46
    利
    1.45
    zunehmen
    1.44
     Öffnungszeiten
    1.44
    URUS
    1.42
    Activations Density 0.010%

    No Known Activations