© 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. 31-GEMMASCOPE-2-RES-262K
    7. 55680
    Prev
    Next
    INDEX
    Explanations

    doing, healing, offers, advice

    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
    麿
    0.51
     ควร
    0.47
     сра
    0.44
     потре
    0.42
    💂
    0.41
    énom
    0.40
    当時
    0.40
     divest
    0.40
    ьера
    0.40
     미래
    0.40
    POSITIVE LOGITS
    RE
    0.49
    في
    0.48
     ওষুধের
    0.47
    Press
    0.47
    ли
    0.45
    ழ
    0.45
    ન
    0.43
     hormones
    0.42
    ات
    0.41
    actions
    0.41
    Activations Density 0.002%

    No Known Activations