© 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. 42012
    Prev
    Next
    INDEX
    Explanations

    first person perspective

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

    agreement and conclusion

    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
    hits
    0.42
    Saint
    0.41
    作
    0.40
    ᵛ
    0.39
     вместо
    0.38
    United
    0.38
    ค
    0.38
    ἢ
    0.38
    makes
    0.37
     результа
    0.37
    POSITIVE LOGITS
    也不能
    0.42
    뭣
    0.41
     veggie
    0.41
     rigidly
    0.40
     Obviously
    0.40
     veggies
    0.40
     hiszen
    0.39
     eben
    0.39
     Inspection
    0.38
     সময়ই
    0.38
    Activations Density 0.002%

    No Known Activations