© 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. 79450
    Prev
    Next
    INDEX
    Explanations

    detachment from external influences

    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
     rozwoju
    0.46
    habilitation
    0.42
     baseHP
    0.42
    ^{\#
    0.40
     wohl
    0.40
    -#
    0.39
     Halsey
    0.38
     healing
    0.38
    }^{\#
    0.38
     friendships
    0.37
    POSITIVE LOGITS
    เปลี่ยนแปลง
    0.43
     label
    0.39
    attachments
    0.39
    вое
    0.38
     attachments
    0.38
     Zustand
    0.38
     disturbances
    0.38
     detach
    0.38
     Attractions
    0.38
     labeling
    0.37
    Activations Density 0.090%

    No Known Activations