© 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. 161085
    Prev
    Next
    INDEX
    Explanations

    shipped on, reserved for

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

    IP address, resources, ask, control

    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
    рида
    0.53
    ంచెం
    0.50
    শিংটন
    0.50
     underestimates
    0.49
     rekao
    0.49
    𝔬
    0.47
    রাজনৈতিক
    0.47
     глубо
    0.46
     nėra
    0.46
    மரு
    0.46
    POSITIVE LOGITS
     spinster
    0.50
    Observers
    0.45
    >∈</
    0.44
     belliger
    0.43
    Clk
    0.42
    合法
    0.42
     શક્ય
    0.41
    购
    0.40
    Iterations
    0.40
    ลูกค้า
    0.39
    Activations Density 0.000%

    No Known Activations