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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3592
    Prev
    Next
    INDEX
    Explanations

    gentle touch and embrace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     hallucinations
    0.90
     illusions
    0.87
     blacks
    0.86
    igamma
    0.85
     showrooms
    0.84
    衅
    0.84
     blanks
    0.83
     gambling
    0.83
     sitcom
    0.82
    蚣
    0.81
    POSITIVE LOGITS
    🫂
    0.87
     Gentle
    0.82
     tagli
    0.81
     gentle
    0.81
     abrazo
    0.81
     embrace
    0.81
     gently
    0.80
     holde
    0.77
     clasp
    0.77
     wrap
    0.76
    Activations Density 0.536%

    No Known Activations