© 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. 31799
    Prev
    Next
    INDEX
    Explanations

    introduces a statement or quote

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

    preventative mental health

    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
    ื้น
    0.42
    িব
    0.37
     curving
    0.37
    MLLoader
    0.36
    },$
    0.36
     observatory
    0.36
    ավ
    0.35
    ímenes
    0.35
    SUV
    0.34
     frontage
    0.34
    POSITIVE LOGITS
     gekennzeichnet
    0.45
     Shoes
    0.44
     thở
    0.44
     Christ
    0.42
     बनें
    0.42
     Christopher
    0.41
    㧡
    0.41
     trotz
    0.40
     Manoj
    0.40
     letz
    0.39
    Activations Density 0.000%

    No Known Activations