© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    acknowledging sensitive or serious input

    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
    剤
    0.47
     Verfahren
    0.46
    できます
    0.45
    oprotein
    0.45
    cein
    0.43
    その他の
    0.42
     anderem
    0.42
    △
    0.42
    Potential
    0.41
    they
    0.41
    POSITIVE LOGITS
     heartbreaking
    0.80
     disappointing
    0.72
     fortunate
    0.72
     certainly
    0.70
     commendable
    0.69
     Undoubtedly
    0.67
     probably
    0.66
     Thankfully
    0.66
     disheart
    0.66
     undoubtedly
    0.65
    Activations Density 0.057%

    No Known Activations