© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 19753
    Prev
    Next
    INDEX
    Explanations

    LINQ or Linode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    ចាប់
    0.41
    串
    0.38
     eject
    0.38
    منت
    0.37
     इंस
    0.36
    लय
    0.36
    দায়
    0.35
    ափ
    0.35
    arity
    0.35
    })_{
    0.34
    POSITIVE LOGITS
     linen
    0.48
    νο
    0.46
     Linen
    0.45
    ux
    0.45
    xu
    0.42
    ters
    0.42
    elizmente
    0.42
     linens
    0.41
    uz
    0.40
     রাগ
    0.40
    Activations Density 0.001%

    No Known Activations