© 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. 134792
    Prev
    Next
    INDEX
    Explanations

    upgrading, differences, double text

    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
    <0xBC>
    0.42
     transcriptional
    0.42
    šnje
    0.41
    plc
    0.40
    ciences
    0.39
     sphinct
    0.38
    straße
    0.38
    strasse
    0.38
     pabb
    0.37
     $($
    0.37
    POSITIVE LOGITS
     Text
    0.49
     Double
    0.44
    Double
    0.43
     Mont
    0.40
     Yarn
    0.40
    double
    0.39
     Triple
    0.39
    amboo
    0.39
     text
    0.38
     डबल
    0.37
    Activations Density 0.000%

    No Known Activations