© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    said, same, current, past

    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
     ostensibly
    1.06
     decidedly
    0.99
     [§
    0.95
     vám
    0.88
     nominally
    0.84
    yip
    0.83
     (“
    0.83
    altering
    0.79
    }={\
    0.78
     χωρίς
    0.78
    POSITIVE LOGITS
     respective
    1.13
     उक्त
    1.08
     aforesaid
    1.06
     obtained
    0.97
     said
    0.93
     same
    0.93
     equipments
    0.92
     whole
    0.91
     following
    0.91
    前記
    0.91
    Activations Density 0.066%

    No Known Activations