© 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. 12575
    Prev
    Next
    INDEX
    Explanations

    animal lovers

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

    comes home

    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
     বলিয়াই
    0.47
    <unused984>
    0.44
    <unused295>
    0.42
    ště
    0.42
    <unused297>
    0.42
     assass
    0.41
    相同
    0.40
    𝒏
    0.40
    
    0.40
    <unused654>
    0.40
    POSITIVE LOGITS
     woord
    0.49
     tatt
    0.47
    decken
    0.45
    眉头
    0.45
    Els
    0.44
    Platform
    0.44
    licer
    0.44
     ers
    0.44
    Ch
    0.43
     polyphen
    0.43
    Activations Density 0.000%

    No Known Activations