© 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. 122995
    Prev
    Next
    INDEX
    Explanations

    dates and titles

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

    blocks to, Serb population, perpetually creating

    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
    رك
    0.46
     положения
    0.46
    ernum
    0.45
     unwilling
    0.45
     ena
    0.45
    哈
    0.44
    摳
    0.43
    規定
    0.42
     في
    0.42
    }/>
    0.42
    POSITIVE LOGITS
     każdy
    0.49
    ವುದ
    0.49
     PARA
    0.48
    screenshot
    0.47
    ም።
    0.46
    ٰی
    0.46
    ній
    0.45
     quilted
    0.45
     なら
    0.45
    ATORS
    0.45
    Activations Density 0.000%

    No Known Activations