© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 142489
    Prev
    Next
    INDEX
    Explanations

    Bruce Lee or airplane mode

    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
     tient
    0.44
     espress
    0.43
     rangle
    0.43
     expressive
    0.43
     grammat
    0.42
    .
    0.42
     unsuccessful
    0.41
     repris
    0.41
     indiscrimin
    0.41
     chocolat
    0.40
    POSITIVE LOGITS
    t
    0.50
     對
    0.49
     వర్
    0.48
     সুর
    0.48
     ရှိ
    0.45
    طي
    0.45
    herjee
    0.45
     γ
    0.45
     ప్రభావ
    0.45
    ত্যা
    0.44
    Activations Density 0.000%

    No Known Activations