© 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. 220167
    Prev
    Next
    INDEX
    Explanations

    as per IRS or follows

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

    cultural, ideal, nostalgic, confidence

    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
     प्रकाश
    0.50
     Protecting
    0.48
     Վ
    0.48
    </h2>
    0.47
     Poems
    0.47
    Thriller
    0.46
    Poems
    0.46
    আমার
    0.46
    ක
    0.46
    ས
    0.46
    POSITIVE LOGITS
     pina
    0.54
    <0x80>
    0.51
     circa
    0.49
    じた
    0.47
    ifix
    0.45
    льного
    0.44
     fateful
    0.44
     tinge
    0.44
     hayas
    0.44
    circa
    0.44
    Activations Density 0.000%

    No Known Activations