© 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
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2595
    Prev
    Next
    INDEX
    Explanations

    explaining steps

    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
     was
    2.81
    佢
    2.69
     she
    2.67
     wid
    2.62
     its
    2.46
     her
    2.36
    orter
    2.33
     we
    2.32
     nous
    2.32
    Nous
    2.31
    POSITIVE LOGITS
    }°
    3.13
     workpiece
    2.79
     newfound
    2.60
    irti
    2.50
     carboxylic
    2.40
    benzoic
    2.39
    ahertz
    2.35
     surroundings
    2.35
    壹章
    2.33
     makeSound
    2.30
    Activations Density 0.352%

    No Known Activations