© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3474
    Prev
    Next
    INDEX
    Explanations

    phishing, phrasal, phalan, phobos, phased

    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_53_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
    riram
    0.40
     fär
    0.39
    iers
    0.38
    ichni
    0.36
    푼
    0.36
     Fär
    0.35
    iami
    0.35
    稠
    0.35
    stige
    0.35
    sliding
    0.35
    POSITIVE LOGITS
    araoh
    0.64
     Ph
    0.63
     ph
    0.60
     PH
    0.59
    ased
    0.59
    antoms
    0.58
    Ph
    0.54
    rases
    0.54
     PHA
    0.54
    ph
    0.53
    Activations Density 0.055%

    No Known Activations