© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77911
    Prev
    Next
    INDEX
    Explanations

    lifting us

    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
     U
    0.46
     Audrey
    0.45
    nées
    0.45
    aines
    0.43
     Magellan
    0.43
    U
    0.42
     Claude
    0.42
    ographies
    0.42
     Lois
    0.42
     caméra
    0.42
    POSITIVE LOGITS
     adenocarcinoma
    0.43
    ]],
    0.41
    かい
    0.38
     contamin
    0.38
     malignancy
    0.37
    JSPA
    0.37
    🏫
    0.36
    Conserv
    0.35
    cardNumber
    0.35
    Groups
    0.35
    Activations Density 0.001%

    No Known Activations