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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 3059
    Prev
    Next
    INDEX
    Explanations

    man who

    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_12_width_65k_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
    <h3>
    1.94
    @
    1.93
    ©
    1.91
    She
    1.89
    shows
    1.86
    Former
    1.84
     shows
    1.83
    Meanwhile
    1.82
    print
    1.82
    ™.
    1.80
    POSITIVE LOGITS
    )]
    1.25
    Соцмережа
    1.19
    )])
    1.10
    циа
    1.07
    ]')
    1.07
    هایت
    1.07
    }))$
    1.05
    _)
    1.05
    鐙
    1.04
    ٧
    1.03
    Activations Density 0.098%

    No Known Activations