© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222695
    Prev
    Next
    INDEX
    Explanations

    specific conditions

    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
    ୯
    0.40
    pert
    0.39
    ulae
    0.38
     relevant
    0.37
    answ
    0.37
    istit
    0.36
    kopf
    0.36
    ewidth
    0.36
     involving
    0.36
     Targeted
    0.36
    POSITIVE LOGITS
    俆
    0.46
     الجميع
    0.42
     paire
    0.42
     yath
    0.41
     humiliation
    0.41
     pés
    0.41
     humiliating
    0.41
     пользоваться
    0.40
     măsur
    0.40
     大家
    0.40
    Activations Density 0.001%

    No Known Activations