© 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. 38196
    Prev
    Next
    INDEX
    Explanations

    Samsung devices and education

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

    understanding concepts and processes

    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
     periphery
    0.47
    riven
    0.44
     CIR
    0.44
     TED
    0.43
    %
    0.42
     NX
    0.41
    {
    0.40
    溯
    0.40
    elli
    0.39
     segmented
    0.39
    POSITIVE LOGITS
    CharPtr
    0.49
     Healing
    0.49
    কত
    0.48
    mongoUrl
    0.47
     ఇచ్చ
    0.46
    MsgCallBack
    0.46
    తిక
    0.46
     বাতিল
    0.46
    μα
    0.46
     Usually
    0.46
    Activations Density 0.001%

    No Known Activations