© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30039
    Prev
    Next
    INDEX
    Explanations

    governmental organizations and NGOs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     have
    0.82
     are
    0.74
    3
    0.66
    sonsten
    0.64
    }$.
    0.64
    }$,
    0.61
     erhe
    0.60
     đều
    0.59
     peligro
    0.59
    च्या
    0.59
    POSITIVE LOGITS
    ل
    1.02
    t
    0.99
    ing
    0.98
    <0x80>
    0.95
    H
    0.91
    us
    0.88
    Z
    0.85
    ર
    0.83
    W
    0.81
    த
    0.81
    Activations Density 0.008%

    No Known Activations