© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48254
    Prev
    Next
    INDEX
    Explanations

    PEM and PGP delimiters

    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_40_width_65k_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
    劒
    0.45
     promoting
    0.41
    (**
    0.40
     अभिव्यक्ति
    0.39
    нче
    0.38
    aap
    0.38
     शीर्ष
    0.38
    Greeting
    0.38
     promote
    0.37
    नमस्कार
    0.37
    POSITIVE LOGITS
     On
    0.59
    On
    0.54
     At
    0.52
     -----
    0.49
    At
    0.47
     tanggal
    0.44
     skrev
    0.44
     بتاريخ
    0.43
     "-----
    0.42
     schrieb
    0.42
    Activations Density 0.009%

    No Known Activations