© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6738
    Prev
    Next
    INDEX
    Explanations

    secrets and hidden information

    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_31_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
    <0x80>
    0.63
    ０
    0.61
     Sper
    0.60
    ти
    0.56
     Seda
    0.56
     Gew
    0.55
     Zur
    0.55
     Telefon
    0.55
     Bernd
    0.55
    <0xAB>
    0.54
    POSITIVE LOGITS
    Secrets
    1.27
     secrets
    1.24
    secrets
    1.18
     secret
    1.06
    secret
    1.05
     secretos
    1.01
    SECRET
    0.96
     비밀
    0.96
     Secrets
    0.95
     secrete
    0.95
    Activations Density 0.068%

    No Known Activations