© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88901
    Prev
    Next
    INDEX
    Explanations

    spaghettification, Paul, theory, Jones, expression

    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
    >
    0.93
     fertil
    0.91
     préstamo
    0.82
     regalo
    0.72
    fNil
    0.71
     recoge
    0.71
    feliz
    0.71
    t
    0.71
     mostr
    0.70
     pagare
    0.70
    POSITIVE LOGITS
    )،
    0.88
    е
    0.80
    а
    0.74
    ة
    0.73
    ">=</
    0.73
    ை
    0.73
    3
    0.72
    使用
    0.72
    ק
    0.71
     argumentation
    0.70
    Activations Density 0.001%

    No Known Activations