© 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. 31191
    Prev
    Next
    INDEX
    Explanations

    text messages

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

    climbing, water, moisture, budget, love

    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
     corroborate
    0.44
    リエ
    0.43
    验
    0.43
    ль
    0.43
    мни
    0.42
     expts
    0.41
    史
    0.41
     extraordin
    0.40
     сообщил
    0.40
    简洁
    0.40
    POSITIVE LOGITS
    უშ
    0.49
     করিত
    0.47
     രണ്ട്
    0.47
     মাধ্যমিক
    0.46
     ಎರಡು
    0.46
     จังหวัด
    0.45
    ysteine
    0.45
    Workout
    0.45
     ד
    0.45
     dichloromethane
    0.45
    Activations Density 0.000%

    No Known Activations