© 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. 184352
    Prev
    Next
    INDEX
    Explanations

    higher than average

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

    electricity, blocks, catches, decimated, hungry

    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
     छि
    0.45
    ਟੀ
    0.45
    ιλ
    0.44
     পছন্দের
    0.44
    泾
    0.44
     মাল
    0.43
     vencer
    0.43
     దూ
    0.42
    孀
    0.42
     keres
    0.42
    POSITIVE LOGITS
     emotionally
    0.51
    OWL
    0.49
     猫
    0.48
    TimeUnit
    0.47
     heartily
    0.47
     the
    0.47
    ce
    0.46
    engined
    0.46
     estuary
    0.46
    ure
    0.45
    Activations Density 0.000%

    No Known Activations