© 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. 135520
    Prev
    Next
    INDEX
    Explanations

    setup fee

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

    methods rely, cycle when, root chords, surprisingly variable, their durability

    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
    encana
    0.48
    bae
    0.46
    莧
    0.45
    克兰
    0.45
    nonumber
    0.44
     पटाखों
    0.43
    pessoas
    0.43
    嬌
    0.43
     ανο
    0.42
    avkh
    0.42
    POSITIVE LOGITS
     этой
    0.55
     Außerdem
    0.49
     этого
    0.49
     Includes
    0.49
    इसमें
    0.48
     binds
    0.48
     bruge
    0.47
     Binding
    0.47
     this
    0.47
     dieser
    0.46
    Activations Density 0.000%

    No Known Activations