© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1584
    Prev
    Next
    INDEX
    Explanations

    public method and function declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ত্ত্ব
    0.42
    !।
    0.42
    ጲ
    0.40
     crossbow
    0.39
    Voids
    0.38
    ])).
    0.38
    픔
    0.38
    Fishing
    0.38
     Voyages
    0.38
    LOUIS
    0.38
    POSITIVE LOGITS
     function
    0.89
    function
    0.80
    /**
    0.63
     public
    0.57
     función
    0.55
     /**
    0.54
    public
    0.54
    use
    0.53
     Function
    0.52
     funzione
    0.51
    Activations Density 0.005%

    No Known Activations