© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11570
    Prev
    Next
    INDEX
    Explanations

    empty parentheses or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    both
    -1.13
    臵
    -1.12
     alip
    -1.11
    without
    -1.09
    ฀
    -1.09
    OOOO
    -1.09
     ferti
    -1.08
    idk
    -1.07
    OOOOO
    -1.05
     formen
    -1.05
    POSITIVE LOGITS
    ();
    1.29
    }-\
    1.22
    Földrajz
    1.18
    ());
    1.16
    };
    1.16
    ");
    1.13
    ];
    1.09
    );
    
    1.09
    ciclop
    1.08
    }
    
    1.07
    Activations Density 0.006%

    No Known Activations