© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36263
    Prev
    Next
    INDEX
    Explanations

    authentication and verification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    rust
    0.38
    Characteristics
    0.37
     زائ
    0.36
    嗉
    0.36
     دنبال
    0.35
    LinkLabel
    0.35
    プラグ
    0.35
    اؤن
    0.35
    +](
    0.34
    sendKeyDown
    0.34
    POSITIVE LOGITS
     verification
    0.48
     login
    0.47
     authenticated
    0.46
     verify
    0.46
     verified
    0.44
     verificar
    0.42
    Login
    0.42
     verificare
    0.42
     Verification
    0.42
    verified
    0.41
    Activations Density 0.001%

    No Known Activations