© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14244
    Prev
    Next
    INDEX
    Explanations

    analogy, difference, June, login

    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_22_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
     потер
    1.10
     hongos
    1.02
     sicuro
    1.01
     terminó
    1.00
    नगर
    1.00
     hacemos
    1.00
    騫
    0.99
     프로
    0.99
     spé
    0.98
     manhã
    0.96
    POSITIVE LOGITS
    ities
    0.94
    drawn
    0.89
    nen
    0.89
    alten
    0.85
    tenance
    0.84
    য়েল
    0.84
    ীর
    0.81
    েলের
    0.81
    ală
    0.80
    provided
    0.80
    Activations Density 0.000%

    No Known Activations