© 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. 201837
    Prev
    Next
    INDEX
    Explanations

    common word pairs

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

    vulnerable to

    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
    мати
    0.57
    ঠোর
    0.50
    ту
    0.43
     muerte
    0.43
     mantiene
    0.42
    ब्बे
    0.42
    キ
    0.42
    뵌
    0.41
    חי
    0.41
    포츠
    0.41
    POSITIVE LOGITS
     الموسم
    0.50
     വാർത്ത
    0.48
     ২০২২
    0.48
     แจ
    0.48
     मे
    0.48
     outfitted
    0.47
     террито
    0.47
     informing
    0.47
     assortment
    0.46
     κ
    0.46
    Activations Density 0.000%

    No Known Activations