© 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. 68330
    Prev
    Next
    INDEX
    Explanations

    predicting image models and scores

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

    making predictions

    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
    Construct
    0.46
    Construction
    0.44
    Growth
    0.44
    成就
    0.44
    עד
    0.43
    лянчук
    0.43
    Literatura
    0.43
    雙
    0.43
    Lesson
    0.43
    ศาส
    0.42
    POSITIVE LOGITS
     predict
    0.58
     predicts
    0.56
     predictions
    0.55
     prediction
    0.53
     predicted
    0.51
     detached
    0.50
     tourists
    0.47
     vectorized
    0.47
     clf
    0.47
     vectors
    0.46
    Activations Density 0.006%

    No Known Activations