© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3843
    Prev
    Next
    INDEX
    Explanations

    Koninklijkeeligibility friendly friendly

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

    Likelihood

    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_53_width_65k_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
    AdType
    0.39
    бой
    0.39
    যন্ত্র
    0.38
    ÂN
    0.37
     Duck
    0.37
    批发
    0.36
    Beverungen
    0.36
    ++];
    0.36
    quinone
    0.35
     Exc
    0.35
    POSITIVE LOGITS
    elig
    1.43
    ELIG
    1.34
    elige
    1.23
    elijk
    1.20
    elijke
    1.13
     eligibility
    1.07
    kelig
    1.07
    Elig
    1.00
     Eligibility
    0.99
    Eligibility
    0.99
    Activations Density 0.005%

    No Known Activations