© 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. 3128
    Prev
    Next
    INDEX
    Explanations

    addresses, abbreviations, or introductory words

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

    HOME crisis line

    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
    ş
    0.71
    ſs
    0.59
    și
    0.56
    şi
    0.53
    ऱ्या
    0.51
    şe
    0.49
    😗
    0.49
    š
    0.48
    ة
    0.48
     estup
    0.46
    POSITIVE LOGITS
    ER
    0.75
    IA
    0.61
    ORY
    0.61
    1
    0.60
    ED
    0.59
    LE
    0.58
    {
    0.55
    VER
    0.54
    ON
    0.54
    INE
    0.53
    Activations Density 0.349%

    No Known Activations