© 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. 98153
    Prev
    Next
    INDEX
    Explanations

    how to, market trends, risk analysis

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

    Okay, let's break down

    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
     посе
    0.45
    阿
    0.42
     увиде
    0.41
     menyaksikan
    0.41
     Seeing
    0.41
     ninth
    0.40
     leak
    0.40
     ham
    0.40
     leaky
    0.40
    abra
    0.39
    POSITIVE LOGITS
    लेट्स
    0.52
     recop
    0.50
    ﾝ
    0.49
    DE
    0.48
     dụng
    0.47
     ദ
    0.47
    actéristiques
    0.46
    凊
    0.46
     Goldberg
    0.45
    Shown
    0.45
    Activations Density 0.001%

    No Known Activations