© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9191
    Prev
    Next
    INDEX
    Explanations

    blood, indigenous, immigration

    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
    로
    2.35
    ан
    2.13
    ă
    2.11
    त
    2.06
    𝘢
    1.97
    는
    1.95
    ę
    1.86
    𝘶
    1.84
    ations
    1.80
    quela
    1.79
    POSITIVE LOGITS
    doa
    2.19
    tipo
    2.06
    ঞ্চলিক
    2.06
     homomorphism
    2.05
    taining
    2.01
    tts
    2.00
    quarters
    2.00
    %%%%%%%%%%%%
    1.98
     decomposing
    1.98
    ्योपै
    1.95
    Activations Density 0.026%

    No Known Activations