© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    years grades through

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

    oldschool talk, been touched

    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
     /-
    0.45
    Nad
    0.44
     jat
    0.39
     narod
    0.39
     Cim
    0.39
    IRT
    0.39
    erler
    0.38
    renti
    0.37
    ″]
    0.36
    ingress
    0.36
    POSITIVE LOGITS
    有点
    0.47
    有點
    0.41
    ToArray
    0.41
     sleeping
    0.40
     אין
    0.40
     Judy
    0.39
     ravaged
    0.39
     необ
    0.38
     cheated
    0.38
     গাড়
    0.38
    Activations Density 0.000%

    No Known Activations