© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 18
    Prev
    Next
    INDEX
    Explanations

    lists concepts and specifics

    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
    }$
    0.96
    ри
    0.93
    И
    0.92
    на
    0.91
    ↵↵
    0.90
    р
    0.89
    }$.
    0.87
    以免
    0.87
    خ
    0.86
    お
    0.85
    POSITIVE LOGITS
     recognizes
    0.87
    য়ের
    0.86
    য়ের
    0.85
    nın
    0.85
     depicts
    0.84
    ますが
    0.82
    icultural
    0.82
    ﻪ
    0.81
     carbide
    0.81
    groupBox
    0.79
    Activations Density 2.927%

    No Known Activations