© 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. 112058
    Prev
    Next
    INDEX
    Explanations

    answer questions

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

    responses to greetings

    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
    진다
    0.47
    έχ
    0.45
    는다
    0.44
     Samples
    0.44
    屜
    0.44
     midrange
    0.43
     Switches
    0.42
    mate
    0.42
    劑
    0.42
    mates
    0.42
    POSITIVE LOGITS
    BufOffset
    0.55
     kurul
    0.49
     desco
    0.48
    ParaName
    0.47
     negoci
    0.47
     gamb
    0.46
    годно
    0.46
     sør
    0.45
     Serikat
    0.45
     verdes
    0.44
    Activations Density 0.000%

    No Known Activations