© 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. 68604
    Prev
    Next
    INDEX
    Explanations

    words preceding descriptive terms

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

    memories, remember, gratitude, fed, started, red, marriage, blueberries, predict

    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
    :(
    0.50
    ijl
    0.49
    XM
    0.47
     TREND
    0.46
     WEST
    0.46
     RECORD
    0.44
    :
    0.44
     EXPRESS
    0.44
    TREND
    0.44
    ?
    0.43
    POSITIVE LOGITS
    enapi
    0.51
     uniquement
    0.50
     mengakses
    0.50
    эс
    0.49
     persönliche
    0.49
     connecté
    0.48
    owość
    0.48
     تطوير
    0.48
    ເພດ
    0.47
    обс
    0.47
    Activations Density 0.001%

    No Known Activations