© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8210
    Prev
    Next
    INDEX
    Explanations

    describes state or quality

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

    code organization

    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_31_width_262k_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
    .").
    0.47
     వంటి
    0.46
    ).”
    0.45
     പോലുള്ള
    0.45
    .);
    0.44
    .”)
    0.44
    ®.
    0.44
    )”.
    0.43
    .’
    0.42
     مثل
    0.42
    POSITIVE LOGITS
     itself
    0.47
     name
    0.46
    টিকে
    0.44
    টির
    0.44
    本身
    0.44
    টিতে
    0.43
     phare
    0.40
    ارد
    0.39
    んですが
    0.39
    本身的
    0.38
    Activations Density 0.259%

    No Known Activations