© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 574
    Prev
    Next
    INDEX
    Explanations

    close personal relationships

    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_16k_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
    0
    0.63
     data
    0.61
     usable
    0.59
     user
    0.58
     ASCII
    0.56
     unusable
    0.56
     alphanumeric
    0.55
     users
    0.55
     algorithms
    0.53
     effiz
    0.53
    POSITIVE LOGITS
    💑
    0.92
     가족
    0.91
     परिवार
    0.90
     família
    0.90
     കുടുംബ
    0.89
     keluarga
    0.88
     사랑
    0.84
     любви
    0.82
     семье
    0.82
     family
    0.82
    Activations Density 1.190%

    No Known Activations