© 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. 8943
    Prev
    Next
    INDEX
    Explanations

    parentheses or followed by abbreviations

    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
    %>
    0.91
    }:
    0.87
    </tr>
    0.87
    >.
    0.85
    ]:
    0.84
    ）：
    0.80
    :}
    0.80
    \]
    0.80
    :]
    0.80
    ):
    0.78
    POSITIVE LOGITS
     (
    3.69
    （
    2.97
    (
    2.72
     （
    2.61
     ((
    2.49
     ([
    2.35
     (-
    2.26
    '(
    2.22
     (#
    2.22
    ₁(
    2.16
    Activations Density 0.391%

    No Known Activations