© 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. 213060
    Prev
    Next
    INDEX
    Explanations

    funeral cortege

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

    crucial setting, functioning normally, quick message

    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
     CLEAR
    0.45
    Clear
    0.45
    Mét
    0.44
    ቖ
    0.44
    Finger
    0.43
    Ton
    0.42
    嶄
    0.42
    㖅
    0.42
    Barn
    0.42
    Tiger
    0.42
    POSITIVE LOGITS
    tbody
    0.54
    oxyde
    0.54
    dilate
    0.53
    neurs
    0.52
    δί
    0.51
    deposited
    0.50
    1
    0.50
    members
    0.49
    releases
    0.48
    acids
    0.48
    Activations Density 0.000%

    No Known Activations