© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131004
    Prev
    Next
    INDEX
    Explanations

    forgetting original capabilities

    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_40_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
    tsz
    0.41
     nazw
    0.40
     નિય
    0.39
     takich
    0.39
     electricity
    0.38
     mushrooms
    0.38
    j
    0.38
     parfait
    0.37
     dessins
    0.37
    raster
    0.37
    POSITIVE LOGITS
     WOMEN
    0.46
     NEO
    0.43
     Mastery
    0.42
    ᵚ
    0.41
     эшлә
    0.41
     QUILL
    0.40
     Women
    0.39
     pioneering
    0.39
    <unused1881>
    0.39
    aruh
    0.39
    Activations Density 0.003%

    No Known Activations