© 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. 177677
    Prev
    Next
    INDEX
    Explanations

    mathematician, dessert, American, Valjean

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

    negative societal issues and sensitive topics

    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
    apaccay
    0.47
     Come
    0.45
    !»
    0.44
     inkább
    0.43
     Prints
    0.43
    Come
    0.43
    滨
    0.42
    皆さん
    0.42
    桫
    0.42
     semuanya
    0.42
    POSITIVE LOGITS
    சால
    0.45
    gamer
    0.44
     footballer
    0.42
    किशोर
    0.42
     метод
    0.42
    ಡಿಯ
    0.42
     perpetrators
    0.42
    nostic
    0.42
     dishonesty
    0.41
     سرطان
    0.41
    Activations Density 0.001%

    No Known Activations