© 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. 71632
    Prev
    Next
    INDEX
    Explanations

    . followed by a word

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

    identifying new conditions

    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
     haben
    0.51
     gratification
    0.51
    x
    0.51
     Verkauf
    0.50
     solicited
    0.48
     disappointed
    0.47
     lanz
    0.46
     Künstler
    0.46
     Quint
    0.45
     αποτε
    0.45
    POSITIVE LOGITS
    abhavam
    0.48
    timestep
    0.47
    ygons
    0.47
    rène
    0.47
    iqui
    0.43
    addy
    0.42
     النسبيه
    0.41
    鐘
    0.41
    ϩ
    0.41
    ឬ
    0.41
    Activations Density 0.001%

    No Known Activations