© 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. 100046
    Prev
    Next
    INDEX
    Explanations

    create lists or datasets

    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
     Whatever
    0.41
    Whatever
    0.40
    મને
    0.39
     whatever
    0.38
    Irish
    0.36
     impossibility
    0.36
    yczny
    0.36
    Þ
    0.35
    CZ
    0.35
     Capsules
    0.35
    POSITIVE LOGITS
     lectura
    0.42
     leitura
    0.41
     actúa
    0.40
    geven
    0.39
    comand
    0.38
     একত্র
    0.38
    Personendaten
    0.37
     oluyor
    0.37
    olare
    0.37
    தார
    0.37
    Activations Density 0.000%

    No Known Activations