© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88889
    Prev
    Next
    INDEX
    Explanations

    Wikipedia and product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    positive, CSR, responsible, staking, compatible, smile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glee
    0.52
     aggiungere
    0.49
     Adding
    0.45
     affirme
    0.44
     (|
    0.44
     capaces
    0.42
     capables
    0.41
     adding
    0.41
     resolv
    0.41
     aiut
    0.40
    POSITIVE LOGITS
    лектрон
    0.46
    迟
    0.44
    开始了
    0.43
    вален
    0.42
     első
    0.42
     cartão
    0.41
    behör
    0.41
    ренко
    0.41
    рии
    0.41
    onerror
    0.41
    Activations Density 0.001%

    No Known Activations