© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96883
    Prev
    Next
    INDEX
    Explanations

    interests and items

    np_acts-logits-general · gemini-2.5-flash-lite

    topic differentiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diversify
    0.46
    ど
    0.44
     Beds
    0.42
    検討
    0.41
     diverg
    0.41
    どう
    0.41
    chicken
    0.40
    lection
    0.40
     enfermed
    0.40
    するには
    0.40
    POSITIVE LOGITS
     PRL
    0.52
     IPO
    0.50
     Baroque
    0.50
    hö
    0.50
     Wahrheit
    0.49
    隆
    0.49
    ตา
    0.48
    峦
    0.48
     ö
    0.48
     PDEs
    0.48
    Activations Density 0.002%

    No Known Activations