© 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. 32105
    Prev
    Next
    INDEX
    Explanations

    advertising designs

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

    incredibly disruptive, been thinking

    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
     देखभाल
    0.44
     लिखित
    0.39
    ране
    0.38
    儚
    0.37
     समाप्ति
    0.36
    ਡ
    0.36
     लर्न
    0.36
    絭
    0.36
    മോ
    0.36
    <unused1810>
    0.35
    POSITIVE LOGITS
     this
    0.52
     is
    0.45
     indicates
    0.43
     attracted
    0.42
     denotes
    0.41
     greeted
    0.40
    is
    0.40
     artists
    0.40
     Note
    0.39
     этого
    0.39
    Activations Density 0.000%

    No Known Activations