© 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. 84750
    Prev
    Next
    INDEX
    Explanations

    subsequent dose of opiates

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

    internal states and structure

    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
    公演
    0.45
    チケット
    0.44
     নামের
    0.43
    耂
    0.43
    考虑
    0.42
     conformance
    0.42
     وجہ
    0.41
    ticket
    0.40
    पया
    0.40
     perdere
    0.40
    POSITIVE LOGITS
    lení
    0.42
    lytres
    0.41
    Yea
    0.40
    embrance
    0.40
    ⏤
    0.39
     captivity
    0.37
    ♫
    0.36
     Vaill
    0.36
     てる
    0.36
    élix
    0.36
    Activations Density 0.000%

    No Known Activations