© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 578
    Prev
    Next
    INDEX
    Explanations

    quantifiers and articles

    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_9_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
    </tr>
    1.15
    ↵
    1.07
    nect
    1.05
    }:
    1.04
    arp
    0.99
    е
    0.99
    }}
    0.98
     andere
    0.97
    со
    0.97
    }`);
    0.96
    POSITIVE LOGITS
    在
    1.57
    The
    1.53
     spearheaded
    1.45
     miraculously
    1.42
     στις
    1.36
    Į
    1.36
     την
    1.33
    Several
    1.32
    From
    1.31
    許多
    1.31
    Activations Density 3.168%

    No Known Activations