© 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. 12561
    Prev
    Next
    INDEX
    Explanations

    numbers, grades, seasons, or years

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

    person, role, age, or specification

    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
    𝘱
    0.42
    рио
    0.38
     basado
    0.38
    çam
    0.38
     บวก
    0.38
     বিবেচনায়
    0.38
     cioè
    0.37
    parametri
    0.37
    OSED
    0.37
    он
    0.35
    POSITIVE LOGITS
     another
    0.50
    5
    0.47
    6
    0.47
    3
    0.43
     Another
    0.42
     ANOTHER
    0.42
    another
    0.41
     sophomore
    0.41
    4
    0.40
    7
    0.39
    Activations Density 0.335%

    No Known Activations