© 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. 75068
    Prev
    Next
    INDEX
    Explanations

    letters and intent

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

    explaining other options incorrect

    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
    第七
    0.60
     recomiendo
    0.55
    𝗘
    0.55
    𝗩
    0.54
    𝘿
    0.53
    ᴊ
    0.53
    ◹
    0.52
    స్ట
    0.52
    ଭ
    0.50
    ეთ
    0.50
    POSITIVE LOGITS
    ate
    0.61
    ial
    0.53
    nxt
    0.47
    ata
    0.47
    orm
    0.46
    imu
    0.46
    asing
    0.45
    iy
    0.45
    ags
    0.44
    ari
    0.44
    Activations Density 0.001%

    No Known Activations