© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62572
    Prev
    Next
    INDEX
    Explanations

    classes after "The", Beatles after "The", bass after "tenor,"

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

    target entities and multilingual text

    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
     mér
    0.41
    rụ
    0.38
     appar
    0.38
     þei
    0.38
    anii
    0.37
    ètes
    0.37
    垩
    0.37
     metų
    0.36
     yam
    0.36
     shik
    0.36
    POSITIVE LOGITS
    Mà
    0.37
    सन
    0.35
     कहलाता
    0.35
    Д
    0.35
     кана
    0.35
    ROUND
    0.34
     개발
    0.34
     Policing
    0.34
    敺
    0.34
    Მ
    0.34
    Activations Density 0.002%

    No Known Activations