© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9963
    Prev
    Next
    INDEX
    Explanations

    local addresses and cloud services

    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_9_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
    🆁
    0.93
     debacle
    0.82
     extrapolation
    0.81
    ayla
    0.80
     tally
    0.80
     அதே
    0.79
    Ꮜ
    0.79
    甛
    0.78
     eviction
    0.78
    ﻛ
    0.78
    POSITIVE LOGITS
    erà
    0.79
    2
    0.78
    nera
    0.76
    いますが
    0.76
    ρια
    0.76
    اً
    0.76
    0
    0.76
     supersede
    0.75
    Į
    0.75
    +'
    0.74
    Activations Density 0.010%

    No Known Activations