© 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. 12152
    Prev
    Next
    INDEX
    Explanations

    hair and follicles

    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
    휼
    0.53
    晠
    0.53
     नाबाद
    0.52
     खरेदी
    0.52
     abstracto
    0.52
    getBlueTeam
    0.52
     पोकेमॉन
    0.48
     уйный
    0.47
    🏛
    0.47
     crédito
    0.47
    POSITIVE LOGITS
     hair
    1.32
     hairs
    1.18
     Hair
    1.17
    Hair
    1.13
    hair
    1.10
     hirs
    1.03
     HAIR
    0.95
     alopecia
    0.95
     follicles
    0.93
     shampoo
    0.91
    Activations Density 0.063%

    No Known Activations