© 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. 67739
    Prev
    Next
    INDEX
    Explanations

    discussion of conclusions

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

    predicting new information

    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
     remit
    0.50
     publicized
    0.47
    謁
    0.47
     webcast
    0.46
     sabah
    0.46
     sensitization
    0.45
    存款
    0.45
     citizenship
    0.45
     remittance
    0.45
     jeopardy
    0.44
    POSITIVE LOGITS
     காற்று
    0.46
    izione
    0.44
     ጋር
    0.43
     በእ
    0.43
     北欧
    0.41
    硞
    0.40
     imágenes
    0.39
     जानवर
    0.39
    ைக
    0.38
    уса
    0.38
    Activations Density 0.002%

    No Known Activations