© 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. 31-GEMMASCOPE-2-RES-262K
    7. 136148
    Prev
    Next
    INDEX
    Explanations

    Merlin Group company names

    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_31_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
    )^{
    0.43
    ivational
    0.43
     liters
    0.42
    जीवी
    0.41
    fuck
    0.41
     |_
    0.41
     एंड
    0.41
     लड़की
    0.41
     merda
    0.41
     °
    0.39
    POSITIVE LOGITS
    Ross
    0.46
    ғ
    0.45
    Bard
    0.44
     Hare
    0.42
     Croft
    0.42
    Hare
    0.41
    Wil
    0.41
    Rose
    0.39
     Upton
    0.39
    Adrian
    0.39
    Activations Density 0.000%

    No Known Activations