© 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-65K
    7. 52035
    Prev
    Next
    INDEX
    Explanations

    states of going away or ending

    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_65k_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
    યું
    0.38
    一些
    0.38
    tzmann
    0.37
    ໃ
    0.37
    ຕໍ່
    0.37
    0.36
    amin
    0.36
    ());
    0.36
     jauh
    0.35
    柚
    0.35
    POSITIVE LOGITS
     become
    0.46
     nonprofit
    0.46
     diventare
    0.45
     privado
    0.43
    become
    0.42
     frankly
    0.42
     authoritarian
    0.41
     philanthropic
    0.41
     devenir
    0.40
     becomes
    0.40
    Activations Density 0.021%

    No Known Activations