© 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. 204725
    Prev
    Next
    INDEX
    Explanations

    data, flavour, complexity, images

    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
     nincs
    0.45
    Solving
    0.43
    тири
    0.43
    dire
    0.42
    Investigators
    0.42
    しますが
    0.42
    निय
    0.41
    /-}$
    0.41
    drunk
    0.41
    Challenges
    0.40
    POSITIVE LOGITS
     determinant
    0.49
    的一些
    0.48
    简单
    0.47
     effective
    0.47
     ended
    0.47
     alcune
    0.46
     infusions
    0.45
     endings
    0.45
     explicit
    0.44
    的一种
    0.44
    Activations Density 0.004%

    No Known Activations