© 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. 17-GEMMASCOPE-2-RES-16K
    7. 14901
    Prev
    Next
    INDEX
    Explanations

    process, pretext, Complete, Runnable, consistently

    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
     outcast
    1.20
     plotted
    1.14
     scars
    1.12
     conceito
    1.11
     mercenary
    1.06
    ᚕ
    0.99
     personagem
    0.99
     judgments
    0.99
     taxonomy
    0.97
     perpetrated
    0.97
    POSITIVE LOGITS
    谕
    1.13
    esses
    1.02
     ilmiah
    0.99
    altern
    0.94
     अनलिमिटेड
    0.93
    ないので
    0.92
    ңы
    0.92
    tere
    0.92
    ਟੀ
    0.92
    ाय
    0.91
    Activations Density 0.004%

    No Known Activations