© 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. 241254
    Prev
    Next
    INDEX
    Explanations

    Trump, measurements, town

    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
     turbulent
    0.50
     Funktions
    0.44
    蝕
    0.44
    ترم
    0.43
    ଲା
    0.42
    </i>
    0.42
    шча
    0.42
     manifestly
    0.41
     Turbulent
    0.40
    电视台
    0.40
    POSITIVE LOGITS
    หรือ
    0.54
    น
    0.50
    usely
    0.49
    uttore
    0.47
    ина
    0.46
    its
    0.46
    ía
    0.46
    abor
    0.46
    โ
    0.45
    った
    0.45
    Activations Density 0.000%

    No Known Activations