© 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. 24088
    Prev
    Next
    INDEX
    Explanations

    giving them over

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

    He also, supply of

    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
    ում
    0.45
     பொழுது
    0.44
    עם
    0.44
    ionization
    0.43
    ני
    0.43
    ראה
    0.43
    ż
    0.43
     분포
    0.42
    dimensioni
    0.42
    Pour
    0.41
    POSITIVE LOGITS
     hará
    0.55
     nhưng
    0.50
     badi
    0.50
     nejs
    0.50
     cauza
    0.50
     Cao
    0.49
     dagger
    0.49
     vali
    0.47
     ESO
    0.47
     dajj
    0.47
    Activations Density 0.000%

    No Known Activations