© 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-3-270M-IT
    3. 15-GEMMASCOPE-2-RES-262K
    4. 70444
    Prev
    Next
    INDEX
    Explanations

    if you've tried

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    uru
    1.26
    �
    1.26
    aro
    1.23
     છીએ
    1.22
    ooo
    1.19
     riot
    1.17
    ao
    1.16
    oooo
    1.15
    \'
    1.11
    ido
    1.11
    POSITIVE LOGITS
    supset
    1.57
    一句
    1.47
     }>
    1.46
    ¹)
    1.45
    })(
    1.43
     any
    1.42
    )>
    1.37
     logros
    1.37
    legas
    1.35
    ()}
    1.35
    Activations Density 0.001%

    No Known Activations