© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4160
    Prev
    Next
    INDEX
    Explanations

    kube, ende, vise, herve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нести
    0.58
    стоит
    0.52
    не
    0.50
    received
    0.50
    radiation
    0.49
    ே
    0.49
    میم
    0.48
    несла
    0.48
    remaining
    0.47
    রে
    0.46
    POSITIVE LOGITS
    aux
    0.70
    ño
    0.65
    urope
    0.64
    ffect
    0.62
    ́
    0.62
    igenschaften
    0.59
    ños
    0.56
    ggi
    0.55
    lectric
    0.55
    instellungen
    0.55
    Activations Density 0.048%

    No Known Activations