© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 224
    Prev
    Next
    INDEX
    Explanations

    could you ask for clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...
    0.94
     O
    0.94
     Até
    0.93
     Frans
    0.93
     prá
    0.91
     Ō
    0.89
     நீர
    0.88
    clé
    0.88
    O
    0.85
     tle
    0.84
    POSITIVE LOGITS
     safegu
    1.22
     utilized
    1.20
     youngsters
    1.14
     sizzling
    1.14
     enchantment
    1.14
     scorching
    1.13
     utilizing
    1.10
     sufferers
    1.09
     payday
    1.08
     america
    1.07
    Activations Density 1.904%

    No Known Activations