© 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. 88805
    Prev
    Next
    INDEX
    Explanations

    concert tickets

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

    next, then, our

    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
     other
    0.20
     других
    0.16
    рган
    0.16
     workpiece
    0.16
     diğer
    0.16
    㴦
    0.16
     altri
    0.16
     інших
    0.15
    <unused208>
    0.15
     flawless
    0.15
    POSITIVE LOGITS
    2
    0.21
    6
    0.19
    -
    0.18
     خدنا
    0.18
     चूंकि
    0.17
     راجس
    0.17
     Anteil
    0.17
     ایالات
    0.17
    9
    0.17
    二人
    0.17
    Activations Density 0.000%

    No Known Activations