© 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. 116358
    Prev
    Next
    INDEX
    Explanations

    certified organic

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

    Wail, music, Chinese

    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
    鹤
    0.47
    鶴
    0.46
     plasmids
    0.45
    坚定
    0.44
     hashCode
    0.44
    芓
    0.44
    少し
    0.43
     sko
    0.42
    olique
    0.42
    ത്തിലൂടെ
    0.42
    POSITIVE LOGITS
     Wail
    0.46
     محاضرت
    0.43
     వర
    0.42
    Waters
    0.41
     Watertown
    0.41
    没人
    0.40
     sheeting
    0.40
    棉
    0.40
     Lies
    0.39
     Gegensatz
    0.39
    Activations Density 0.001%

    No Known Activations