© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162533
    Prev
    Next
    INDEX
    Explanations

    houses, shack, custody, respect, London

    np_acts-logits-general · gemini-2.5-flash-lite

    essentially explains something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]=="
    0.41
    キロ
    0.41
    fought
    0.40
    দানে
    0.39
    enser
    0.39
     zusätzliche
    0.39
    tgts
    0.39
    jskich
    0.39
    radeon
    0.38
    Viele
    0.38
    POSITIVE LOGITS
     {
    0.51
     பாவ
    0.49
     jurispr
    0.47
     cilt
    0.47
     вес
    0.46
     каран
    0.46
     prostit
    0.45
     abst
    0.44
     tavern
    0.44
     ل
    0.44
    Activations Density 0.001%

    No Known Activations