© 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. 194662
    Prev
    Next
    INDEX
    Explanations

    year projections, stereo measurement, fear Allah

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

    OpenAI API, character names

    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
    지
    0.52
    ﭼ
    0.51
    Бе
    0.50
    ällä
    0.47
    Rustic
    0.47
    ي
    0.47
    没有
    0.46
    ເຂົ້າ
    0.45
    ه
    0.45
    يا
    0.44
    POSITIVE LOGITS
    ORICAL
    0.50
     inspirations
    0.42
    affe
    0.41
     fortuna
    0.41
    Encript
    0.40
     widescreen
    0.40
    OLA
    0.40
    ליה
    0.39
    ODES
    0.39
     카메라
    0.39
    Activations Density 0.000%

    No Known Activations