© 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
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1136
    Prev
    Next
    INDEX
    Explanations

    integration within systems

    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
     (’
    1.53
     (‘
    1.50
     (`
    1.50
     (£
    1.45
     (/
    1.42
     wasn
    1.42
     ``
    1.39
     (\"
    1.39
    ﹗
    1.38
     (=
    1.37
    POSITIVE LOGITS
     lugar
    1.95
     andar
    1.90
    8
    1.89
     terren
    1.86
    7
    1.85
    3
    1.83
    ilize
    1.82
    nsan
    1.77
    6
    1.76
     iniciar
    1.75
    Activations Density 0.390%

    No Known Activations