© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54125
    Prev
    Next
    INDEX
    Explanations

    declarative knowledge and facts

    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
    differ
    0.42
     publisher
    0.40
     সংখ্যাগ
    0.40
     [...
    0.37
    publisher
    0.37
    scanning
    0.37
    adress
    0.36
    program
    0.36
     Indianapolis
    0.36
     MAY
    0.35
    POSITIVE LOGITS
     näch
    0.44
     מו
    0.41
     гуляць
    0.41
    âche
    0.39
     Europese
    0.39
     जलाशय
    0.38
    ☓
    0.38
    êmes
    0.38
     Nā
    0.38
     новой
    0.38
    Activations Density 0.005%

    No Known Activations