© 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. 222251
    Prev
    Next
    INDEX
    Explanations

    abortions, bombings, sclerosis

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

    ids and data fields

    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
    pInBuffer
    0.47
    ARON
    0.44
    ﹏
    0.43
    মূল
    0.42
    COOL
    0.41
    সমান
    0.41
    вале
    0.41
     guar
    0.41
    EditText
    0.41
    ByDefault
    0.41
    POSITIVE LOGITS
     minder
    0.50
     Stopped
    0.48
     lokal
    0.47
    ewalk
    0.46
     berhenti
    0.46
     abortions
    0.45
    凝
    0.45
     sclerosis
    0.43
    zeptember
    0.43
     bombings
    0.43
    Activations Density 0.001%

    No Known Activations